Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1172ba164c682a3e0dd729d7a9a22faf4464c66cf306d5567f76f8298446497
+oid sha256:5020a9931778de46324a519ce7cfc9b9531c49659d1f4d660e4e4dcf9af73e6e
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36684bf6dd4ea8c22918a1273e56901b5eef8c7c2670d4c49847f54559506bab
+oid sha256:d8b346efddef7b332a8c64b55c5890d2aac7400cdc220a679b420ea48896a82f
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0ccefc184fa295de1a2d6489564c75170c52e5faed488c5d05875798de8bbd0
+oid sha256:4a0e9196076a0d33158d55fa00ca33962c552978cb699e7103837784568481cb
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85d5e97e64d0e6dc454145514f54be879a521d22e1d7d97ef85d77d9ccc20d23
+oid sha256:4bb9a89e6b1c071895881a8b9cc961153cb9179e0ed596b7a5fd026d52390909
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69637d48dad1c14ef28286f5a52e43ae2ff3ca4107ae32300c7426bffae35b16
+oid sha256:75598c4096b09664079954a202f9da53bdc19f2f93b86de1ce248f7b2b8249d1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05f1008a2109b5931112ed09d9497f17bf465a3e4167c01562585f68431b8f5c
+oid sha256:0cc00cbb08356c2d963dea23aaedc571f70b613a20ffc519a62b103aabc3486f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06396929473852551,
+  "epoch": 0.12793858947705103,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 72.25,
       "eval_steps_per_second": 9.055,
       "step": 25
+    },
+    {
+      "epoch": 0.06652806652806653,
+      "grad_norm": 1.6729117631912231,
+      "learning_rate": 5e-05,
+      "loss": 0.1896,
+      "step": 26
+    },
+    {
+      "epoch": 0.06908683831760755,
+      "grad_norm": 0.7531017661094666,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0992,
+      "step": 27
+    },
+    {
+      "epoch": 0.07164561010714857,
+      "grad_norm": 0.862877607345581,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0977,
+      "step": 28
+    },
+    {
+      "epoch": 0.07420438189668958,
+      "grad_norm": 1.5235896110534668,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0702,
+      "step": 29
+    },
+    {
+      "epoch": 0.07676315368623061,
+      "grad_norm": 1.0583374500274658,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.052,
+      "step": 30
+    },
+    {
+      "epoch": 0.07932192547577163,
+      "grad_norm": 1.06094229221344,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0453,
+      "step": 31
+    },
+    {
+      "epoch": 0.08188069726531265,
+      "grad_norm": 0.7197346687316895,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0613,
+      "step": 32
+    },
+    {
+      "epoch": 0.08443946905485367,
+      "grad_norm": 1.0249391794204712,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0762,
+      "step": 33
+    },
+    {
+      "epoch": 0.08699824084439468,
+      "grad_norm": 1.1629976034164429,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.102,
+      "step": 34
+    },
+    {
+      "epoch": 0.08955701263393571,
+      "grad_norm": 0.8161555528640747,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0485,
+      "step": 35
+    },
+    {
+      "epoch": 0.09211578442347673,
+      "grad_norm": 0.7493521571159363,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0812,
+      "step": 36
+    },
+    {
+      "epoch": 0.09467455621301775,
+      "grad_norm": 1.0272088050842285,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0908,
+      "step": 37
+    },
+    {
+      "epoch": 0.09723332800255877,
+      "grad_norm": 1.7803131341934204,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1749,
+      "step": 38
+    },
+    {
+      "epoch": 0.0997920997920998,
+      "grad_norm": 1.0670037269592285,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0817,
+      "step": 39
+    },
+    {
+      "epoch": 0.10235087158164081,
+      "grad_norm": 0.6444293260574341,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0544,
+      "step": 40
+    },
+    {
+      "epoch": 0.10490964337118183,
+      "grad_norm": 0.5108956098556519,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0574,
+      "step": 41
+    },
+    {
+      "epoch": 0.10746841516072285,
+      "grad_norm": 0.7616376876831055,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0522,
+      "step": 42
+    },
+    {
+      "epoch": 0.11002718695026387,
+      "grad_norm": 0.6766124367713928,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0396,
+      "step": 43
+    },
+    {
+      "epoch": 0.1125859587398049,
+      "grad_norm": 0.7287461757659912,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0636,
+      "step": 44
+    },
+    {
+      "epoch": 0.11514473052934592,
+      "grad_norm": 1.3630841970443726,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0857,
+      "step": 45
+    },
+    {
+      "epoch": 0.11770350231888693,
+      "grad_norm": 1.068311333656311,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.082,
+      "step": 46
+    },
+    {
+      "epoch": 0.12026227410842795,
+      "grad_norm": 1.1175423860549927,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0288,
+      "step": 47
+    },
+    {
+      "epoch": 0.12282104589796898,
+      "grad_norm": 0.9052390456199646,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0743,
+      "step": 48
+    },
+    {
+      "epoch": 0.12537981768751,
+      "grad_norm": 0.9554215669631958,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0632,
+      "step": 49
+    },
+    {
+      "epoch": 0.12793858947705103,
+      "grad_norm": 1.0501782894134521,
+      "learning_rate": 0.0,
+      "loss": 0.0551,
+      "step": 50
+    },
+    {
+      "epoch": 0.12793858947705103,
+      "eval_loss": NaN,
+      "eval_runtime": 72.5923,
+      "eval_samples_per_second": 36.271,
+      "eval_steps_per_second": 4.546,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.94731890081792e+16,
+  "total_flos": 1.589463780163584e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null