Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cfa554076dbc955812b29e11dde2b51aeaa1784f294a44b94ee8a5c55aee6bd
+oid sha256:d84bca271ca6da822aedb10315d06a0a63330433b969ac9d3cb454e6d1ca9639
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9b8918f7224ab6c7744b614bbca9b5da82d16373719ec6ef257db57891448f4
+oid sha256:12bd310f40aa55ba02a368992a8a260dd02d3246ac3446f890ab4935a8b31bb4
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2008a75cb5dd5d8e6402990beb1748d1bf46fc447f0eaeb2c4cf2f7794d1897e
+oid sha256:1c06d15ff9b633b68ebbf688949ae28d38f1d004fd46f5c3de3aeed397a80edf
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
+oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9371306300163269,
-  "best_model_checkpoint": "./outputs/checkpoint-2000",
-  "epoch": 2.6666666666666665,
+  "best_metric": 0.9311172366142273,
+  "best_model_checkpoint": "./outputs/checkpoint-2100",
+  "epoch": 2.8,
   "eval_steps": 100,
-  "global_step": 2000,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,6 +287,20 @@
       "eval_samples_per_second": 2.113,
       "eval_steps_per_second": 0.265,
       "step": 2000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 0.0002,
+      "loss": 0.7534,
+      "step": 2100
+    },
+    {
+      "epoch": 2.8,
+      "eval_loss": 0.9311172366142273,
+      "eval_runtime": 913.8258,
+      "eval_samples_per_second": 2.112,
+      "eval_steps_per_second": 0.265,
+      "step": 2100
     }
   ],
   "logging_steps": 100,
@@ -294,7 +308,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.1806097015361536e+17,
+  "total_flos": 5.4402852955938816e+17,
   "trial_name": null,
   "trial_params": null
 }