Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bac3e8316cf3415aff07cf2de9f2178932d236471a9809d3aa85cc05fcc59c6
+oid sha256:577eeac7a60ed7599a3e24eab1088a6aec9136fe0fda2bbaf1eaecd1a8f30af9
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0917b7387490b1f1af3c51292c4ee53e956fe707dfd9346fb5de55817d3e9a44
+oid sha256:ff52efa99847ec91136934067727db0624573392fc1f6c1ddd87f1c96fc345d2
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9f2e9cfc489ab39b06d1f7093738f22710b5eb729d191272ce46a91be4a256c
+oid sha256:85d056193496956e8b170c3a63327049be7976e3085c0472d1887964b7bf481a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006358782048669139,
+  "epoch": 0.008152284677780949,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 1.0772,
       "step": 35
+    },
+    {
+      "epoch": 0.006521827742224758,
+      "grad_norm": 0.7148851752281189,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1107,
+      "step": 40
+    },
+    {
+      "epoch": 0.006521827742224758,
+      "eval_loss": 1.120132565498352,
+      "eval_runtime": 98.2234,
+      "eval_samples_per_second": 26.297,
+      "eval_steps_per_second": 13.154,
+      "step": 40
+    },
+    {
+      "epoch": 0.0073370562100028534,
+      "grad_norm": 0.7597112655639648,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0479,
+      "step": 45
+    },
+    {
+      "epoch": 0.008152284677780949,
+      "grad_norm": 0.608223021030426,
+      "learning_rate": 0.0,
+      "loss": 1.0353,
+      "step": 50
+    },
+    {
+      "epoch": 0.008152284677780949,
+      "eval_loss": 1.1179903745651245,
+      "eval_runtime": 99.164,
+      "eval_samples_per_second": 26.048,
+      "eval_steps_per_second": 13.029,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1509423109373952.0,
+  "total_flos": 1954432312934400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null