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:a558cc8e94c2bc8a26cf1ff79f5e8d2d50b2439aeafc1b573656e46bf0714e12
+oid sha256:8afd024bd40848a862ec36e2daeb73a08ce75d4bd6a09cdf81674d077e55aad2
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeafd0e9c7dbc91c280e25cd573fab1af6afa8f0c1c5171918b489a7781d3c92
+oid sha256:1e77cb5b035661a89b4514fdf704ceaf178f2f3af5004def3d7f80f11ba0cc5d
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a1c67ad35beaa20b431c3f0fd87f64c74aaef3138f7a8e0b4724cc5df848627
+oid sha256:ed540e83ce76c319a2ea9abff579a1fc6e35c796a15fa63c666dc8578da55a97
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c54c8f7543783bc39a163d29ab61f460e19cf79f6b8ef99bcd4741a9f8c07bd
+oid sha256:a064318792055fb18a5a0fb953f66a3cee70dd757ffcb95fcbce4acaab835b52
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a707536fa657b3408632f0843ee3626cd3217fec98a848e3128f43efae503a7
+oid sha256:ab3a462f279f7284d59fff369eb25b114ebb59de2633d7839b449d1fb676fd8d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9b65f4e7e43d3d1adecf4857574d27c760de825944b777ac1a3858ff32a86ad
+oid sha256:c9bcbd33e9627f98155a79af66c07bb2ff3031878264c5076fa39edaecfd7437
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03971405877680699,
+  "epoch": 0.07942811755361398,
   "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": 14.259,
       "eval_steps_per_second": 3.707,
       "step": 25
+    },
+    {
+      "epoch": 0.04130262112787927,
+      "grad_norm": 0.7342965602874756,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.1988,
+      "step": 26
+    },
+    {
+      "epoch": 0.04289118347895155,
+      "grad_norm": 0.7945647239685059,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.2555,
+      "step": 27
+    },
+    {
+      "epoch": 0.04447974583002383,
+      "grad_norm": 0.6723583340644836,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.2587,
+      "step": 28
+    },
+    {
+      "epoch": 0.046068308181096106,
+      "grad_norm": 0.5241828560829163,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.2403,
+      "step": 29
+    },
+    {
+      "epoch": 0.04765687053216839,
+      "grad_norm": 0.36510878801345825,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.1623,
+      "step": 30
+    },
+    {
+      "epoch": 0.04924543288324067,
+      "grad_norm": 0.3164938986301422,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.1624,
+      "step": 31
+    },
+    {
+      "epoch": 0.050833995234312944,
+      "grad_norm": 0.30257853865623474,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.2095,
+      "step": 32
+    },
+    {
+      "epoch": 0.05242255758538523,
+      "grad_norm": 0.3617624044418335,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.1691,
+      "step": 33
+    },
+    {
+      "epoch": 0.054011119936457505,
+      "grad_norm": 0.45267167687416077,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.2001,
+      "step": 34
+    },
+    {
+      "epoch": 0.05559968228752978,
+      "grad_norm": 0.7200210690498352,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.1548,
+      "step": 35
+    },
+    {
+      "epoch": 0.057188244638602066,
+      "grad_norm": 0.7799243927001953,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.1776,
+      "step": 36
+    },
+    {
+      "epoch": 0.05877680698967434,
+      "grad_norm": 0.5142637491226196,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.9758,
+      "step": 37
+    },
+    {
+      "epoch": 0.06036536934074663,
+      "grad_norm": 0.33579036593437195,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.165,
+      "step": 38
+    },
+    {
+      "epoch": 0.061953931691818905,
+      "grad_norm": 0.23867741227149963,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.1552,
+      "step": 39
+    },
+    {
+      "epoch": 0.06354249404289118,
+      "grad_norm": 0.2340697944164276,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.159,
+      "step": 40
+    },
+    {
+      "epoch": 0.06513105639396347,
+      "grad_norm": 0.23957717418670654,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.1161,
+      "step": 41
+    },
+    {
+      "epoch": 0.06671961874503574,
+      "grad_norm": 0.24248702824115753,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.1005,
+      "step": 42
+    },
+    {
+      "epoch": 0.06830818109610802,
+      "grad_norm": 0.2694977819919586,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.199,
+      "step": 43
+    },
+    {
+      "epoch": 0.0698967434471803,
+      "grad_norm": 0.26048219203948975,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.1541,
+      "step": 44
+    },
+    {
+      "epoch": 0.07148530579825259,
+      "grad_norm": 0.30306071043014526,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.1597,
+      "step": 45
+    },
+    {
+      "epoch": 0.07307386814932486,
+      "grad_norm": 0.32802388072013855,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.1397,
+      "step": 46
+    },
+    {
+      "epoch": 0.07466243050039714,
+      "grad_norm": 0.3386339247226715,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.1361,
+      "step": 47
+    },
+    {
+      "epoch": 0.07625099285146943,
+      "grad_norm": 0.4382065236568451,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.1027,
+      "step": 48
+    },
+    {
+      "epoch": 0.0778395552025417,
+      "grad_norm": 0.44363492727279663,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.0657,
+      "step": 49
+    },
+    {
+      "epoch": 0.07942811755361398,
+      "grad_norm": 0.5245867967605591,
+      "learning_rate": 1e-05,
+      "loss": 0.9692,
+      "step": 50
+    },
+    {
+      "epoch": 0.07942811755361398,
+      "eval_loss": 1.1204785108566284,
+      "eval_runtime": 3.5107,
+      "eval_samples_per_second": 14.242,
+      "eval_steps_per_second": 3.703,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,12 +395,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.984974321220321e+17,
+  "total_flos": 5.969948642440643e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null