Training in progress, step 136, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f48e5e504da172c01e6ee3da031e8a9cae7d2213f5cb8705cf8cc99dc402c40
+oid sha256:a76f914b47be02a1f65f43bf3479c04fbd79e2f88b877c3b16a685626b7ad331
 size 692136856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edaa271176ce862e004df1f0dc773f6ce9648c87c722df370b11c98cad47b292
+oid sha256:8f257dd9e0289db79f785ec4853e1f1fd36aff06829c616d2869899bfbaee54d
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b472766fb64a3faca824302324f58abb5e35dea39174d7a492c6d7c52b86b41c
+oid sha256:99174d59b2f745e4fca8944695e995f5b82e2541faeac9696a55b797d641e61d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baea37709b071cdabc5712824dc3f783ecd30d18a1e0d85c4d56cfebfa22b7e0
+oid sha256:2f676b917baa0a895f62d4ea12d985f19fe259f840a0ba6d41d00cece68314f5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006872852233676976,
+  "epoch": 0.009163802978235968,
   "eval_steps": 34,
-  "global_step": 102,
+  "global_step": 136,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -277,6 +277,91 @@
       "eval_samples_per_second": 14.031,
       "eval_steps_per_second": 1.754,
       "step": 102
+    },
+    {
+      "epoch": 0.007074994946432181,
+      "grad_norm": 0.7040189504623413,
+      "learning_rate": 4.303006118359537e-05,
+      "loss": 0.8247,
+      "step": 105
+    },
+    {
+      "epoch": 0.0072771376591873865,
+      "grad_norm": 0.7915964722633362,
+      "learning_rate": 4.260632628966974e-05,
+      "loss": 0.8551,
+      "step": 108
+    },
+    {
+      "epoch": 0.007479280371942592,
+      "grad_norm": 0.7852084040641785,
+      "learning_rate": 4.217230979699188e-05,
+      "loss": 0.8425,
+      "step": 111
+    },
+    {
+      "epoch": 0.007681423084697796,
+      "grad_norm": 0.6728894114494324,
+      "learning_rate": 4.172826515897146e-05,
+      "loss": 0.8141,
+      "step": 114
+    },
+    {
+      "epoch": 0.007883565797453002,
+      "grad_norm": 0.7391681671142578,
+      "learning_rate": 4.12744516851726e-05,
+      "loss": 0.7987,
+      "step": 117
+    },
+    {
+      "epoch": 0.008085708510208208,
+      "grad_norm": 0.7469043135643005,
+      "learning_rate": 4.0811134389884433e-05,
+      "loss": 0.7909,
+      "step": 120
+    },
+    {
+      "epoch": 0.008287851222963412,
+      "grad_norm": 0.7632879614830017,
+      "learning_rate": 4.0338583837360225e-05,
+      "loss": 0.8031,
+      "step": 123
+    },
+    {
+      "epoch": 0.008489993935718617,
+      "grad_norm": 0.7656901478767395,
+      "learning_rate": 3.985707598381544e-05,
+      "loss": 0.843,
+      "step": 126
+    },
+    {
+      "epoch": 0.008692136648473823,
+      "grad_norm": 0.8024786114692688,
+      "learning_rate": 3.9366892016277096e-05,
+      "loss": 0.8403,
+      "step": 129
+    },
+    {
+      "epoch": 0.008894279361229027,
+      "grad_norm": 0.6944208145141602,
+      "learning_rate": 3.886831818837847e-05,
+      "loss": 0.7908,
+      "step": 132
+    },
+    {
+      "epoch": 0.009096422073984234,
+      "grad_norm": 0.719901442527771,
+      "learning_rate": 3.8361645653195026e-05,
+      "loss": 0.8151,
+      "step": 135
+    },
+    {
+      "epoch": 0.009163802978235968,
+      "eval_loss": 0.8194563388824463,
+      "eval_runtime": 1782.0949,
+      "eval_samples_per_second": 14.026,
+      "eval_steps_per_second": 1.754,
+      "step": 136
     }
   ],
   "logging_steps": 3,
@@ -296,7 +381,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4343849987224371e+17,
+  "total_flos": 1.912513331629916e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null