Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbac07c54af71b1523ccefd010ed4fa8f29f41bccaf7f00fb9a8c48c135a05e9
+oid sha256:3e7d0e90a80b69667359fdf8fe0c2f1e8e9576e12ef16cdf3ee0146c07cfeef2
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c288537365d7d6c7fdaf368f5b2b898c07485a5f0c1b7a22ef52e77417be877
+oid sha256:e4f332b4ef0cc3a7c9d7cdc440819b3e1c311c3f1323ca0018a9a5424bd71067
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2780285db9dcbedfa558cb2cf6f7a6604eabefd92d06bfa1eb702ad38e4c4f00
+oid sha256:b708b72239765e2913894959f4b9fc75f2825e61f1491eda436ca51a25bef5f1
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
+oid sha256:30423cc69a1c7d18caef4643847588d5884db012263cbe7b7224fa4719ca4156
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0152662992477417,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.8,
+  "best_metric": 1.0105178356170654,
+  "best_model_checkpoint": "./outputs/checkpoint-700",
+  "epoch": 0.9333333333333333,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,6 +91,20 @@
       "eval_samples_per_second": 2.635,
       "eval_steps_per_second": 0.33,
       "step": 600
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002,
+      "loss": 0.8445,
+      "step": 700
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 1.0105178356170654,
+      "eval_runtime": 802.0691,
+      "eval_samples_per_second": 2.406,
+      "eval_steps_per_second": 0.302,
+      "step": 700
     }
   ],
   "logging_steps": 100,
@@ -98,7 +112,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 100,
-  "total_flos": 1.5536474436108288e+17,
+  "total_flos": 1.81363638199296e+17,
   "trial_name": null,
   "trial_params": null
 }