Training in progress, step 199764, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f117dd565f6ce119a7ab273507fed496c1ef97abf41ab3fb96f3f15b5b093885
+oid sha256:4cf0bcb7d3ca09a342fcfc235067fb20d1a354073e87505ef089ed7c01dffac9
 size 466289280

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f71d9052aaeec7b71e29f501d83441ebfb73ee455b12421e1bd873a3b02bf9a9
+oid sha256:28f493075dd0cae59e97d2a821cbb6a5faf64bb64b5c2e595d84033258f6aefa
 size 932672442

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce643dc83e6406caf3dc96437daf2af7153c2d12a984bc515c067467febc407e
+oid sha256:f877aaf1c908eec1d0705a7a99ec8e0d4860730d9b3fd376717fa6ee89e134dd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dca3aab84aeacc5f3fb66c81b2380fa436b115eecc94206afa3c268d57d32a23
+oid sha256:597d54923f947aa39c4dfbc7d0c69acd0ddad86d19c03796f1545edfaf3e00f9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.800003604269257,
+  "epoch": 0.900004054802914,
   "eval_steps": 500,
-  "global_step": 177568,
+  "global_step": 199764,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -560,6 +560,76 @@
       "learning_rate": 2.0985407214845987e-06,
       "loss": 3.6253,
       "step": 175380
+    },
+    {
+      "epoch": 0.8001477750395344,
+      "grad_norm": 8.387534141540527,
+      "learning_rate": 1.9985222496046567e-06,
+      "loss": 3.6102,
+      "step": 177600
+    },
+    {
+      "epoch": 0.8101496222275285,
+      "grad_norm": 9.557201385498047,
+      "learning_rate": 1.898503777724715e-06,
+      "loss": 3.6088,
+      "step": 179820
+    },
+    {
+      "epoch": 0.8201514694155226,
+      "grad_norm": 8.81215763092041,
+      "learning_rate": 1.7984853058447732e-06,
+      "loss": 3.6092,
+      "step": 182040
+    },
+    {
+      "epoch": 0.8301533166035169,
+      "grad_norm": 5.788514137268066,
+      "learning_rate": 1.6984668339648313e-06,
+      "loss": 3.5987,
+      "step": 184260
+    },
+    {
+      "epoch": 0.840155163791511,
+      "grad_norm": 3.8115339279174805,
+      "learning_rate": 1.5984483620848898e-06,
+      "loss": 3.6097,
+      "step": 186480
+    },
+    {
+      "epoch": 0.8501570109795052,
+      "grad_norm": 9.834037780761719,
+      "learning_rate": 1.498429890204948e-06,
+      "loss": 3.6115,
+      "step": 188700
+    },
+    {
+      "epoch": 0.8601588581674994,
+      "grad_norm": 4.8395586013793945,
+      "learning_rate": 1.398411418325006e-06,
+      "loss": 3.6048,
+      "step": 190920
+    },
+    {
+      "epoch": 0.8701607053554936,
+      "grad_norm": 5.381741523742676,
+      "learning_rate": 1.2983929464450643e-06,
+      "loss": 3.6098,
+      "step": 193140
+    },
+    {
+      "epoch": 0.8801625525434877,
+      "grad_norm": 9.676674842834473,
+      "learning_rate": 1.1983744745651226e-06,
+      "loss": 3.6137,
+      "step": 195360
+    },
+    {
+      "epoch": 0.890164399731482,
+      "grad_norm": 9.529138565063477,
+      "learning_rate": 1.0983560026851806e-06,
+      "loss": 3.6122,
+      "step": 197580
     }
   ],
   "logging_steps": 2220,
@@ -567,7 +637,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 22196,
-  "total_flos": 4.107095329536e+16,
+  "total_flos": 4.6201916348928e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null