Training in progress, step 52, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5db89031f861b351398579fdeed7f2fb75adc951da6bbb79461eec30cb42cae7
+oid sha256:a62eaa1c0aa39c35aed3a646e094cb0c5fd05d6e6bac7bb2bc0582888b4b98fe
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c83434275e79d234627e39a2ec4efe033481954aab821806a1dfd2935bd20358
+oid sha256:98da6b8aaefb6096bb3ab2e07390a761ded121ccf0edee18cbe1c58fa2b509b9
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b699cd69e707818116cdde38e402657f6f0fe8cde3928db61304dd17c81e968e
+oid sha256:601131cde1c22105044011da47a3d843369b7dabae6b9b3a0d5857d64c1ee8c7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb9c3c0c925ea8cf32a1dcba2e2f6242aaac5236534a8df451537dd590ac10a
+oid sha256:a0083f46b3c06809c7ba2e6389d4ff484bc53254e300d739b3ff127153f94c8d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05190268247036806,
+  "epoch": 0.06920357662715741,
   "eval_steps": 50,
-  "global_step": 39,
+  "global_step": 52,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -288,6 +288,105 @@
       "learning_rate": 0.00014223202029717776,
       "loss": 46.5923,
       "step": 39
+    },
+    {
+      "epoch": 0.05323352048242878,
+      "grad_norm": 4.8244147300720215,
+      "learning_rate": 0.0001414092019239907,
+      "loss": 46.1269,
+      "step": 40
+    },
+    {
+      "epoch": 0.0545643584944895,
+      "grad_norm": 4.208717346191406,
+      "learning_rate": 0.00014054760244698884,
+      "loss": 49.8436,
+      "step": 41
+    },
+    {
+      "epoch": 0.05589519650655022,
+      "grad_norm": 3.8489153385162354,
+      "learning_rate": 0.00013964772501600368,
+      "loss": 45.9188,
+      "step": 42
+    },
+    {
+      "epoch": 0.05722603451861094,
+      "grad_norm": 3.9226901531219482,
+      "learning_rate": 0.00013871009513411408,
+      "loss": 45.8486,
+      "step": 43
+    },
+    {
+      "epoch": 0.058556872530671655,
+      "grad_norm": 4.560520172119141,
+      "learning_rate": 0.00013773526035076698,
+      "loss": 46.0863,
+      "step": 44
+    },
+    {
+      "epoch": 0.05988771054273238,
+      "grad_norm": 5.09638786315918,
+      "learning_rate": 0.00013672378994202423,
+      "loss": 45.7102,
+      "step": 45
+    },
+    {
+      "epoch": 0.0612185485547931,
+      "grad_norm": 4.719268321990967,
+      "learning_rate": 0.00013567627457812106,
+      "loss": 45.6349,
+      "step": 46
+    },
+    {
+      "epoch": 0.06254938656685381,
+      "grad_norm": 4.546507835388184,
+      "learning_rate": 0.00013459332597853157,
+      "loss": 47.0023,
+      "step": 47
+    },
+    {
+      "epoch": 0.06388022457891454,
+      "grad_norm": 4.938004970550537,
+      "learning_rate": 0.00013347557655474167,
+      "loss": 42.3119,
+      "step": 48
+    },
+    {
+      "epoch": 0.06521106259097526,
+      "grad_norm": 4.659527778625488,
+      "learning_rate": 0.0001323236790409386,
+      "loss": 46.6489,
+      "step": 49
+    },
+    {
+      "epoch": 0.06654190060303597,
+      "grad_norm": 4.204468727111816,
+      "learning_rate": 0.00013113830611283258,
+      "loss": 45.922,
+      "step": 50
+    },
+    {
+      "epoch": 0.06654190060303597,
+      "eval_loss": 1.4664535522460938,
+      "eval_runtime": 577.3931,
+      "eval_samples_per_second": 4.383,
+      "eval_steps_per_second": 2.193,
+      "step": 50
+    },
+    {
+      "epoch": 0.0678727386150967,
+      "grad_norm": 4.2126569747924805,
+      "learning_rate": 0.00012992014999483302,
+      "loss": 47.7475,
+      "step": 51
+    },
+    {
+      "epoch": 0.06920357662715741,
+      "grad_norm": 4.303404331207275,
+      "learning_rate": 0.00012866992205580908,
+      "loss": 45.0831,
+      "step": 52
     }
   ],
   "logging_steps": 1,
@@ -307,7 +406,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.207202166135849e+17,
+  "total_flos": 2.940197077600174e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null