Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74dbc4fc66a0521c67117b743d8dee6d8791965619a98835f3f2c1874b66cb9c
+oid sha256:3730a1d878d4053b143d57a57c1fac448e69341b9479dfd3f851a6ab33144e33
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38b14e9e9ec67fc84b17a0cf8ac4351485843887f3332aa843d88f8792e88c06
+oid sha256:f89d84528008d151b3dd4170e97962e1d6e21f8f9d5216a258aa552ef4052471
 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 sha256:54ecb14aafa347554d588d4693c91cb65e2015d07059f19d3a2e8bd39a45c1a9
+oid sha256:022b8217d4b55852b997e3b5ca16c9910cfc8e1e5dae3900bbbe1878452b5ee9
 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": 6.845386533665836e-06,
       "loss": 0.3385,
       "step": 9500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.29613471031188965,
+      "eval_runtime": 31.4504,
+      "eval_samples_per_second": 15.707,
+      "eval_steps_per_second": 7.854,
+      "step": 9624
+    },
+    {
+      "epoch": 2.0781379883624274,
+      "grad_norm": 0.6130263209342957,
+      "learning_rate": 6.15267387087836e-06,
+      "loss": 0.3293,
+      "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