Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f95c23974ed9109b85d1dad46b75fc294d57305fa7210035c0b8f9d6d02471c8
+oid sha256:553847da08f4d99da7d19a6b3de5c0bfaddfb192c11023e43e98976448986428
 size 83393928

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73ca5659e648d8d2948c2a5236ec358ca29f5a01082e4ad9696138a21a331db0
+oid sha256:815f38c8915ea63b4c636ccf0bb20219fa79e6d05a12c0e52cd97f9f17abe0a8
 size 166834490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fab47d19446cd54935782c0ac0c7342531b306e31812fb709d49481db05d461
+oid sha256:e784b60e22cd0340bb430f54e442a2113831330be18f972ee8b8be0beda9874d
 size 13990

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff6c50a5de085f119dc1e92af1ad0ce825f5b55602192739818f51a65a78e8d6
+oid sha256:b297641bdf7639a42fd0ab19dc974295f49e08948c929302cee801e3646dd894
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0094758886014536,
+  "epoch": 0.0189517772029072,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -51,6 +51,49 @@
       "eval_samples_per_second": 7.608,
       "eval_steps_per_second": 3.804,
       "step": 500
+    },
+    {
+      "epoch": 0.011371066321744321,
+      "grad_norm": 1.2209495306015015,
+      "learning_rate": 4.981079988376354e-05,
+      "loss": 1.0478,
+      "step": 600
+    },
+    {
+      "epoch": 0.013266244042035042,
+      "grad_norm": 1.0413841009140015,
+      "learning_rate": 4.9779213887730734e-05,
+      "loss": 1.0083,
+      "step": 700
+    },
+    {
+      "epoch": 0.015161421762325763,
+      "grad_norm": 1.0854493379592896,
+      "learning_rate": 4.974762789169794e-05,
+      "loss": 0.9881,
+      "step": 800
+    },
+    {
+      "epoch": 0.017056599482616484,
+      "grad_norm": 0.9769160747528076,
+      "learning_rate": 4.9716041895665136e-05,
+      "loss": 0.9694,
+      "step": 900
+    },
+    {
+      "epoch": 0.0189517772029072,
+      "grad_norm": 1.0413130521774292,
+      "learning_rate": 4.9684455899632343e-05,
+      "loss": 0.9495,
+      "step": 1000
+    },
+    {
+      "epoch": 0.0189517772029072,
+      "eval_loss": 0.9161216616630554,
+      "eval_runtime": 8628.0851,
+      "eval_samples_per_second": 10.872,
+      "eval_steps_per_second": 5.436,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -70,7 +113,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 512075305648128.0,
+  "total_flos": 1026720523419648.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null