Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e22260d65676f915e4958d20419e6e1670fca3c9554454b41e00a01f59036dc8
+oid sha256:d6889ce869137e3d279293e3ffff9f22039ae191700c8265421901a0e6021c3f
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10f0faeafff597195ee7f26d52a60f75e5adf20ceaeaf10787f20bf70ee638b4
+oid sha256:dd548064b42e9bc13e75e6e88004e41384e0a954cdd111e6655e7c700709f114
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2b67c05f37b4606592392a2a2e3555caf2c285ee68c702566e4cb3524218561
+oid sha256:2e2beb5f3eae46760fe93c244c16d7260ed6d437cc6536ace16b095ba9f37e6d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcc9e973441a5ba67c47763b37bce78dd415347becadca5e0c593823cb37a70d
+oid sha256:f9fdfaf4edd9a546b1d0f37b5f883b42cacfc782c11efcb3c34d2675d15c08f7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9742310889443058,
+  "epoch": 2.0781379883624274,
   "eval_steps": 500,
-  "global_step": 9500,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,21 @@
       "learning_rate": 6.844001108340261e-06,
       "loss": 0.3386,
       "step": 9500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.29590198397636414,
+      "eval_runtime": 31.3938,
+      "eval_samples_per_second": 15.736,
+      "eval_steps_per_second": 7.868,
+      "step": 9624
+    },
+    {
+      "epoch": 2.0781379883624274,
+      "grad_norm": 0.6089585423469543,
+      "learning_rate": 6.151288445552786e-06,
+      "loss": 0.3294,
+      "step": 10000
     }
   ],
   "logging_steps": 500,
@@ -167,7 +182,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.156959096274944e+16,
+  "total_flos": 1.217793989541888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null