Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f38413fdf094950efc408c8a4ca57d8d40b355d8089907ca4a8d6751f6a3c194
+oid sha256:52f0a2fc6267937deecd4e28f6482a0100df3ba2d6024141559399cff3e234c9
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84438d412785718fa70f6376e019cccc00c02803f0e3231c958b2990b6947083
+oid sha256:56c48ea34e8e1f7978b2fa1bbc1d3e19e17cbee609e6497b1fc38447a256ae46
 size 18810036

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec7849812afeab7ef6949c30e1c4abc08917a032177e35eef1205e39c5221c6e
+oid sha256:215560264689880257fdb7c8617f72affe41ba766add2cacbdb9ef5c31af674a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4277d379c277b822bd1a84f4195aa4ce7a11338d881cc3a7e8b5c08e5b1a0102
+oid sha256:94b39e8c3c264c7a29205e1143cc420054d6c2a4ccd0b8144d83abbcc8b6f6ba
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad29ab1d363fdb4f0256cc49d9d9946513becf4e959a04438b825eaa45a1c57d
+oid sha256:68bbed80b67563400d0c339f2aeac8b6acb4d6f9bf8cac433d81746ac01dad0d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70d6a60bddaaf5723adcc5545a09ff518db0815b751d4ee2d05ab7118c53548b
+oid sha256:177ef792e0ddb06784c822410339968bdadccad87bb5f2ee4a2bcbf704576a5a
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
+oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06409861325115562,
+  "epoch": 0.09614791987673343,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 140.503,
       "eval_steps_per_second": 17.582,
       "step": 26
+    },
+    {
+      "epoch": 0.06656394453004623,
+      "grad_norm": 0.946167528629303,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.0381,
+      "step": 27
+    },
+    {
+      "epoch": 0.06902927580893682,
+      "grad_norm": 1.160494089126587,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.0201,
+      "step": 28
+    },
+    {
+      "epoch": 0.07149460708782743,
+      "grad_norm": 0.37332940101623535,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 0.022,
+      "step": 29
+    },
+    {
+      "epoch": 0.07395993836671803,
+      "grad_norm": 0.8763566613197327,
+      "learning_rate": 5e-05,
+      "loss": 0.0371,
+      "step": 30
+    },
+    {
+      "epoch": 0.07642526964560863,
+      "grad_norm": 0.07144226133823395,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 0.0063,
+      "step": 31
+    },
+    {
+      "epoch": 0.07889060092449923,
+      "grad_norm": 0.2712821066379547,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.0231,
+      "step": 32
+    },
+    {
+      "epoch": 0.08135593220338982,
+      "grad_norm": 0.79026198387146,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.014,
+      "step": 33
+    },
+    {
+      "epoch": 0.08382126348228043,
+      "grad_norm": 0.7974649667739868,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0096,
+      "step": 34
+    },
+    {
+      "epoch": 0.08628659476117104,
+      "grad_norm": 0.4885225296020508,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0126,
+      "step": 35
+    },
+    {
+      "epoch": 0.08875192604006163,
+      "grad_norm": 0.5886369347572327,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.0296,
+      "step": 36
+    },
+    {
+      "epoch": 0.09121725731895224,
+      "grad_norm": 1.1059995889663696,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.0491,
+      "step": 37
+    },
+    {
+      "epoch": 0.09368258859784284,
+      "grad_norm": 2.0051498413085938,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0301,
+      "step": 38
+    },
+    {
+      "epoch": 0.09614791987673343,
+      "grad_norm": 0.6557801365852356,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.0304,
+      "step": 39
+    },
+    {
+      "epoch": 0.09614791987673343,
+      "eval_loss": 0.022078825160861015,
+      "eval_runtime": 19.4482,
+      "eval_samples_per_second": 140.527,
+      "eval_steps_per_second": 17.585,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.999169891434496e+16,
+  "total_flos": 4.498754837151744e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null