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:aa759fd004ef51f24a25fdac47e61783837e15fb860f797f6f3379ed640dac99
+oid sha256:08c4df2fbbdf3fb1ccebf74c76d420cd99e180e5ad2d691ec1c5d15367ac73be
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca66da990d305c904ac11b6d50968d2204d110abc0ba58e8af862f9fee132f4c
+oid sha256:9412e34f1e45da29f04de22a4d1650a57f046d4363798a2ad47a84e13992675a
 size 12611145

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:773be59c20afd641e7916cd56aeef99133cb59b4168ce3fcef9b62cf2c047e84
+oid sha256:a8cfcaec1f5911fc7c2b7c4eeaf66555768023f53d9ed79d8ed6b38d001dcf35
 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": 1.1837488412857056,
-  "best_model_checkpoint": "./outputs/checkpoint-2000",
-  "epoch": 2.6666666666666665,
+  "best_metric": 1.1784791946411133,
+  "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": 4.234,
       "eval_steps_per_second": 0.531,
       "step": 2000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 0.0002,
+      "loss": 0.966,
+      "step": 2100
+    },
+    {
+      "epoch": 2.8,
+      "eval_loss": 1.1784791946411133,
+      "eval_runtime": 455.9297,
+      "eval_samples_per_second": 4.233,
+      "eval_steps_per_second": 0.531,
+      "step": 2100
     }
   ],
   "logging_steps": 100,
@@ -294,7 +308,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.653895699274138e+16,
+  "total_flos": 6.987573836110234e+16,
   "trial_name": null,
   "trial_params": null
 }