Training in progress, step 1100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60946e37979145aa9a9e215ed9d7164b3fffae876a38c9bd5428998b9e46f967
+oid sha256:181d85e807b0b793a1dc2bb1ecd6f311ed37477246478ab7572f367f6d8eacab
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aac72d3c9ffae1a41075109cb505cc228f79b1166b04ee4f0cb3149b4bc83712
+oid sha256:b8651df2fec8e9e3bc369dd9f51ab3623b928fa3d1963e3a099359ec9cdc0933
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94f62e9a3b242c8c8b9f4a8d4e73fc2bfa679b0c548fab0ee7b833ff28c97b01
+oid sha256:84db2af589fa7f305136bb5605de5c7877cdb6c1ecdd979b15a8d593b1177841
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
+oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9387000799179077,
-  "best_model_checkpoint": "./outputs/checkpoint-1000",
-  "epoch": 1.4204545454545454,
+  "best_metric": 1.9253034591674805,
+  "best_model_checkpoint": "./outputs/checkpoint-1100",
+  "epoch": 1.5625,
   "eval_steps": 100,
-  "global_step": 1000,
+  "global_step": 1100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,20 @@
       "eval_samples_per_second": 19.854,
       "eval_steps_per_second": 2.488,
       "step": 1000
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0002,
+      "loss": 2.0801,
+      "step": 1100
+    },
+    {
+      "epoch": 1.56,
+      "eval_loss": 1.9253034591674805,
+      "eval_runtime": 75.0032,
+      "eval_samples_per_second": 19.892,
+      "eval_steps_per_second": 2.493,
+      "step": 1100
     }
   ],
   "logging_steps": 100,
@@ -154,7 +168,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.04398546665472e+16,
+  "total_flos": 3.347635642638336e+16,
   "trial_name": null,
   "trial_params": null
 }