Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f19a7e503d94f9b64df0560282fbe997e7da73c7968bffb42cfeab5178ae35b
+oid sha256:df2896cd7eb2ec97d098203d43dd30d1d1f73365f05a99b958ba964ea05402e7
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c26cbaaa4e678f05d077806328331aa6a369702496f1c25f3415ec83dbcfa6d0
+oid sha256:4e39947e7a93518dd94a84e177b7ba9040f949f016ef7acccc98f797716d914a
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5225e37d7d543a33e698142d3eeff29567a056e9f14e596173f4a3fbf89f1212
+oid sha256:3ede8a96df203bfaf73cac48d3e45f9f76b2abaa2d6f489ac91c929dd83a9183
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05649717514124294,
+  "epoch": 0.0847457627118644,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 8.776,
       "eval_steps_per_second": 4.388,
       "step": 20
+    },
+    {
+      "epoch": 0.059322033898305086,
+      "grad_norm": 0.7277962565422058,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.566,
+      "step": 21
+    },
+    {
+      "epoch": 0.06779661016949153,
+      "grad_norm": 0.6766118407249451,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.4651,
+      "step": 24
+    },
+    {
+      "epoch": 0.07062146892655367,
+      "eval_loss": 1.5247591733932495,
+      "eval_runtime": 17.0437,
+      "eval_samples_per_second": 8.801,
+      "eval_steps_per_second": 4.4,
+      "step": 25
+    },
+    {
+      "epoch": 0.07627118644067797,
+      "grad_norm": 0.7272737622261047,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.534,
+      "step": 27
+    },
+    {
+      "epoch": 0.0847457627118644,
+      "grad_norm": 0.6504532694816589,
+      "learning_rate": 0.0,
+      "loss": 1.4885,
+      "step": 30
+    },
+    {
+      "epoch": 0.0847457627118644,
+      "eval_loss": 1.5210504531860352,
+      "eval_runtime": 17.1088,
+      "eval_samples_per_second": 8.767,
+      "eval_steps_per_second": 4.384,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2010596581048320.0,
+  "total_flos": 3015894871572480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null