Training in progress, step 20, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4004324ae6a287b56f6750e0088510f56f4e3770c777e917f2b7d91578c5b194
+oid sha256:74482d56d36e465549c20be2150fd2ef4b59d83accfc45b098eea9ef8a38e044
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb823174ab249b1842d4e1162abd6e67ae85179a680cff7991e0b160459185c1
+oid sha256:23d680fefa7597e1b297207c4260840a411a6cf7b773c449f6e2ca2c5e13fb07
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eb579b6634a965331bf4e2fb7490cfab58bd743a2aa0822c6275d43249a9fe6
+oid sha256:40c70e1001ae0e367150867105486fed534a3bc9b59aab53fe74124dba56db2a
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:889f6fc92910dc1617d7e2b8e49ec9358ef58d2162623ab1d55db477fded32fc
+oid sha256:ad4a07c066075e0a1b5d9477b0d2f4d6bab07235ad5efe05720caa179d7171b5
 size 1465

last-checkpoint/trainer_state.json

@@ -2,86 +2,49 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2,
+  "epoch": 0.1,
   "eval_steps": 20,
-  "global_step": 40,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.025,
-      "grad_norm": 0.19855035841464996,
+      "grad_norm": 0.2091294378042221,
       "learning_rate": 1.6e-06,
-      "loss": 22.03577117919922,
+      "loss": 21.9791015625,
       "step": 5
     },
     {
       "epoch": 0.05,
-      "grad_norm": 0.20424452424049377,
+      "grad_norm": 0.21135330200195312,
       "learning_rate": 3.6e-06,
-      "loss": 22.039888000488283,
+      "loss": 21.991165161132812,
       "step": 10
     },
     {
       "epoch": 0.075,
-      "grad_norm": 0.19867758452892303,
+      "grad_norm": 0.2114953100681305,
       "learning_rate": 3.995627254437549e-06,
-      "loss": 22.05139923095703,
+      "loss": 21.989112854003906,
       "step": 15
     },
     {
       "epoch": 0.1,
-      "grad_norm": 0.21107740700244904,
+      "grad_norm": 0.1982107013463974,
       "learning_rate": 3.9778957412029366e-06,
-      "loss": 22.04059600830078,
+      "loss": 21.98875274658203,
       "step": 20
     },
     {
       "epoch": 0.1,
-      "eval_accuracy": 1.978021978021978e-05,
-      "eval_loss": 11.020455360412598,
-      "eval_runtime": 92.6203,
-      "eval_samples_per_second": 10.797,
-      "eval_steps_per_second": 2.699,
+      "eval_accuracy": 1.221001221001221e-05,
+      "eval_loss": 10.98886489868164,
+      "eval_runtime": 91.9166,
+      "eval_samples_per_second": 10.879,
+      "eval_steps_per_second": 1.817,
       "step": 20
-    },
-    {
-      "epoch": 0.125,
-      "grad_norm": 0.204095259308815,
-      "learning_rate": 3.9466531944960116e-06,
-      "loss": 22.034034729003906,
-      "step": 25
-    },
-    {
-      "epoch": 0.15,
-      "grad_norm": 0.19144363701343536,
-      "learning_rate": 3.902113032590307e-06,
-      "loss": 22.034739685058593,
-      "step": 30
-    },
-    {
-      "epoch": 0.175,
-      "grad_norm": 0.20849967002868652,
-      "learning_rate": 3.844579509954769e-06,
-      "loss": 22.041725158691406,
-      "step": 35
-    },
-    {
-      "epoch": 0.2,
-      "grad_norm": 0.1984155923128128,
-      "learning_rate": 3.7744456388872234e-06,
-      "loss": 22.034831237792968,
-      "step": 40
-    },
-    {
-      "epoch": 0.2,
-      "eval_accuracy": 2.0024420024420023e-05,
-      "eval_loss": 11.019495964050293,
-      "eval_runtime": 92.1989,
-      "eval_samples_per_second": 10.846,
-      "eval_steps_per_second": 2.712,
-      "step": 40
     }
   ],
   "logging_steps": 5,
@@ -102,7 +65,7 @@
     }
   },
   "total_flos": 0.0,
-  "train_batch_size": 4,
+  "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff6acc2c85619ab487b0f5352ddad26b9a9f05dd3dec11fa8ed4abb1a5a9ef99
+oid sha256:45a03866db9595121dc0a92697619c52144b0fc40ad7e945dc9cd18869090b4f
 size 5265