Training in progress, step 1100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bad098bfc3580a7ad640c4130e7a07c7506695bf24af2b17c66a370a46a96ea
+oid sha256:e4d69499c5af363db9c69800142daa202a40720097dcebdb876bc14cde7f5d13
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1678b1a77440b4735ea8dca5d633374798805380e60f92032e0e8dfb0faedde
+oid sha256:47615466b0123bdcca71dd3dc26a2fef0b8c8f7445ddb63eaee76e7d029bd403
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f5f93394ec4ac2c9202e96d8f2c28e904b14601df40e2aa991afd31d35337d4
+oid sha256:133aae226bbaac66725e376492ee3f542023abc66dd7536ee6fe5913c3f55ef4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dee088d40e7a433523254925268530a7e4fe462e4869c9eeb52cf75236d3eadf
+oid sha256:050a05f863436bace20199741dad316727f622e89a1193b9d3f3a77dd7cb7646
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.38640429338103754,
+  "epoch": 0.3935599284436494,
   "eval_steps": 500,
-  "global_step": 1080,
+  "global_step": 1100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -871,14 +871,30 @@
       "loss": 0.408,
       "num_input_tokens_seen": 724716,
       "step": 1080
+    },
+    {
+      "epoch": 0.38998211091234347,
+      "grad_norm": 0.35407742857933044,
+      "learning_rate": 0.00012200357781753131,
+      "loss": 0.4088,
+      "num_input_tokens_seen": 730694,
+      "step": 1090
+    },
+    {
+      "epoch": 0.3935599284436494,
+      "grad_norm": 0.36748751997947693,
+      "learning_rate": 0.00012128801431127013,
+      "loss": 0.4208,
+      "num_input_tokens_seen": 739112,
+      "step": 1100
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 724716,
+  "num_input_tokens_seen": 739112,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.6296303583715328e+16,
+  "total_flos": 1.6620018785796096e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null