Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05c9217a6440de93507e45529dbfc7757363e4c3d5c08a4d1a6c2da1410a2aad
+oid sha256:4030e8efe8df2096efa24e91ae9d2dc5259ef3aa43680ba96780a0ec39bbda1d
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53565dfc6511d3d1eac92534fdd0420a2545a035a0c60a3ee6c206a235c4843b
+oid sha256:8ba5f34d02a65b1c2743dde736c3724cdec91892da11a409e39622823aee287b
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5144eb86423bab2f9277d0f38f80e2ba81632bc758578b755b641da5dff4b5b
+oid sha256:1a4efd2bb8b17d04992384081b7c4cb9ac732e0559d63fefc4ed9404afb6d251
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1dd9849ca4eb0bbd0c1826e2446a4a04de55b83629f951a6c395748072082d1
+oid sha256:6d94bafecf7916614803b87d25183784af22e78a3c8769cf9497c7cd53bb0c26
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d96a8d4472ce3a7bcdce4e15b8adbaf27e103050e8c7598cf0748e1168aec53b
+oid sha256:7a7cc68df676ebe221e0a188b8affc86916395f1d5e2594a0f40d54e2bb35b6d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b090041a93f04c0b2532a33e4f9cf0149045785268665b70856f4275eab5400c
+oid sha256:86aca5810e533f6951031117abae149aeb785cc2873a4d259a67e85b564c6433
 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": 0.3276003276003276,
+  "epoch": 0.6552006552006552,
   "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": 75.32,
       "eval_steps_per_second": 9.525,
       "step": 25
+    },
+    {
+      "epoch": 0.3407043407043407,
+      "grad_norm": 1.8005356788635254,
+      "learning_rate": 5e-05,
+      "loss": 0.9829,
+      "step": 26
+    },
+    {
+      "epoch": 0.3538083538083538,
+      "grad_norm": 1.772329568862915,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.3472,
+      "step": 27
+    },
+    {
+      "epoch": 0.3669123669123669,
+      "grad_norm": 1.5069606304168701,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.5007,
+      "step": 28
+    },
+    {
+      "epoch": 0.38001638001638,
+      "grad_norm": 1.6165857315063477,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.1671,
+      "step": 29
+    },
+    {
+      "epoch": 0.3931203931203931,
+      "grad_norm": 1.6595863103866577,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.3591,
+      "step": 30
+    },
+    {
+      "epoch": 0.4062244062244062,
+      "grad_norm": 1.8731105327606201,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.0039,
+      "step": 31
+    },
+    {
+      "epoch": 0.41932841932841936,
+      "grad_norm": 1.8856438398361206,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.4461,
+      "step": 32
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "grad_norm": 1.9924148321151733,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.1221,
+      "step": 33
+    },
+    {
+      "epoch": 0.44553644553644556,
+      "grad_norm": 2.2074906826019287,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.0594,
+      "step": 34
+    },
+    {
+      "epoch": 0.45864045864045866,
+      "grad_norm": 2.3928334712982178,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.1962,
+      "step": 35
+    },
+    {
+      "epoch": 0.47174447174447176,
+      "grad_norm": 2.2513129711151123,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.1857,
+      "step": 36
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 2.4426679611206055,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.1917,
+      "step": 37
+    },
+    {
+      "epoch": 0.49795249795249796,
+      "grad_norm": 1.7712135314941406,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0161,
+      "step": 38
+    },
+    {
+      "epoch": 0.5110565110565111,
+      "grad_norm": 1.5969468355178833,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.955,
+      "step": 39
+    },
+    {
+      "epoch": 0.5241605241605242,
+      "grad_norm": 1.6872109174728394,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.4407,
+      "step": 40
+    },
+    {
+      "epoch": 0.5372645372645373,
+      "grad_norm": 1.7902907133102417,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.2382,
+      "step": 41
+    },
+    {
+      "epoch": 0.5503685503685504,
+      "grad_norm": 1.5357950925827026,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.3056,
+      "step": 42
+    },
+    {
+      "epoch": 0.5634725634725635,
+      "grad_norm": 1.6491217613220215,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.1163,
+      "step": 43
+    },
+    {
+      "epoch": 0.5765765765765766,
+      "grad_norm": 1.644583821296692,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.3071,
+      "step": 44
+    },
+    {
+      "epoch": 0.5896805896805897,
+      "grad_norm": 1.6915448904037476,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.078,
+      "step": 45
+    },
+    {
+      "epoch": 0.6027846027846028,
+      "grad_norm": 1.5991367101669312,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.9096,
+      "step": 46
+    },
+    {
+      "epoch": 0.6158886158886159,
+      "grad_norm": 1.7828935384750366,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.0314,
+      "step": 47
+    },
+    {
+      "epoch": 0.628992628992629,
+      "grad_norm": 1.9073837995529175,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.0454,
+      "step": 48
+    },
+    {
+      "epoch": 0.6420966420966421,
+      "grad_norm": 1.964453935623169,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.0232,
+      "step": 49
+    },
+    {
+      "epoch": 0.6552006552006552,
+      "grad_norm": 2.5052285194396973,
+      "learning_rate": 0.0,
+      "loss": 1.5223,
+      "step": 50
+    },
+    {
+      "epoch": 0.6552006552006552,
+      "eval_loss": NaN,
+      "eval_runtime": 6.8264,
+      "eval_samples_per_second": 75.296,
+      "eval_steps_per_second": 9.522,
+      "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