Training in progress, step 40000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03d397c4a3a41b4709ba927e33c23bd6813d48f33a28912c366d4c11d70efb15
+oid sha256:93944d3da94e747d1eb6729b5cf252c97afb6c5c71c3bb6fb94728dbb93580ad
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fd570247b466e685c3d3098c33daa213d7c6f367d7267bb069e886d5d11ae18
+oid sha256:ae37a541fce5610847044607f6719e0d304a7d22c1474f06c0d42c3e7e858884
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:035410855824f7fc929714ad14168e53d3e5a3e358dbe2adc5c70b54e0734bfa
+oid sha256:e0482616294e14da6847ffaa783531ec334633dfd41edcf1d3d71810b0c98d07
 size 14244

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.945551390806865,
+  "epoch": 7.89110278161373,
   "eval_steps": 20000,
-  "global_step": 20000,
+  "global_step": 40000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,6 +35,34 @@
       "learning_rate": 5e-05,
       "loss": 0.0022,
       "step": 20000
+    },
+    {
+      "epoch": 4.931939238508582,
+      "grad_norm": 0.04711014777421951,
+      "learning_rate": 5e-05,
+      "loss": 0.0016,
+      "step": 25000
+    },
+    {
+      "epoch": 5.918327086210298,
+      "grad_norm": 0.046736110001802444,
+      "learning_rate": 5e-05,
+      "loss": 0.0014,
+      "step": 30000
+    },
+    {
+      "epoch": 6.904714933912015,
+      "grad_norm": 0.0477403923869133,
+      "learning_rate": 5e-05,
+      "loss": 0.0012,
+      "step": 35000
+    },
+    {
+      "epoch": 7.89110278161373,
+      "grad_norm": 0.03815523907542229,
+      "learning_rate": 5e-05,
+      "loss": 0.0011,
+      "step": 40000
     }
   ],
   "logging_steps": 5000,
@@ -54,7 +82,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.733485734532155e+17,
+  "total_flos": 3.4672067032889626e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null