Training in progress, step 1740, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2571cd02811d646143de10022d9d61c8fbf4e91b2e1b761d5e95b98208a7f6ca
+oid sha256:bd26cfe9b646210c60d4811af8b70f3f54f489bec1b95bff978b4f03ee10cad5
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a04b94f32120c904d17b5e7daf6e052525ae04f447d161e67e5960adc6e1237f
+oid sha256:c9d7727bb468ce33cc85c85dbc8bf7fca3716b4e134b773d14e3a430add12064
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a642ee1476531cfd990fb5cb0edacdc4846648718d220ef0934d9434724daa35
+oid sha256:d2754616b85cea2ec4918640d230c479a914b3143b7c0af235eb6e00c51de30f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49f1e0333c6f78fccc02371feb195657c276bb422aba0842abe5ecaa76ddb2c6
+oid sha256:5f5eb12cc8f462347c54ae45e967712ebfb182e1bce4f798acee1ab55a15db33
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6153846153846154,
+  "epoch": 0.6225402504472272,
   "eval_steps": 500,
-  "global_step": 1720,
+  "global_step": 1740,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1383,14 +1383,30 @@
       "loss": 0.399,
       "num_input_tokens_seen": 1159983,
       "step": 1720
+    },
+    {
+      "epoch": 0.6189624329159212,
+      "grad_norm": 0.2761338949203491,
+      "learning_rate": 7.620751341681575e-05,
+      "loss": 0.3954,
+      "num_input_tokens_seen": 1168489,
+      "step": 1730
+    },
+    {
+      "epoch": 0.6225402504472272,
+      "grad_norm": 0.4277167022228241,
+      "learning_rate": 7.549194991055457e-05,
+      "loss": 0.4031,
+      "num_input_tokens_seen": 1175665,
+      "step": 1740
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1159983,
+  "num_input_tokens_seen": 1175665,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.6083921315313664e+16,
+  "total_flos": 2.643655411602432e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null