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:a727b522e35dac37cd1b96f0a1beeaf15c6965fca52676b352f885c758a2ea8b
+oid sha256:4d45168c79085a55cd271b1376e9d7f96a27c313d79aecffaad5c4349ea09569
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:096e4cdc1936b780b8b27fdd5c014e49e17056b3c8ee0fe5964b9b32f2b75056
+oid sha256:e01e28c80a9efe0aa7294f31afefd1b1f595d5fd336ebc54d47d0abc0352ef72
 size 200345450

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff3af6703afef06d3f8140917a81e0b1bae6d756f458e8b329dc225905f091a3
+oid sha256:fdb349cfd5e4bc7dc6b1427841c22b82f8c8fe454b47b791bdf4748e397dcc60
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0012484394506866417,
+  "epoch": 0.0024968789013732834,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,65 @@
       "eval_samples_per_second": 10.45,
       "eval_steps_per_second": 5.226,
       "step": 15
+    },
+    {
+      "epoch": 0.00149812734082397,
+      "grad_norm": 0.9353959560394287,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.7951,
+      "step": 18
+    },
+    {
+      "epoch": 0.0016645859342488557,
+      "eval_loss": 0.7313250303268433,
+      "eval_runtime": 483.8924,
+      "eval_samples_per_second": 10.455,
+      "eval_steps_per_second": 5.228,
+      "step": 20
+    },
+    {
+      "epoch": 0.0017478152309612985,
+      "grad_norm": 0.8403879404067993,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.7052,
+      "step": 21
+    },
+    {
+      "epoch": 0.0019975031210986267,
+      "grad_norm": 0.900141179561615,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.6583,
+      "step": 24
+    },
+    {
+      "epoch": 0.0020807324178110697,
+      "eval_loss": 0.7008999586105347,
+      "eval_runtime": 483.8944,
+      "eval_samples_per_second": 10.455,
+      "eval_steps_per_second": 5.228,
+      "step": 25
+    },
+    {
+      "epoch": 0.0022471910112359553,
+      "grad_norm": 0.8363513350486755,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.635,
+      "step": 27
+    },
+    {
+      "epoch": 0.0024968789013732834,
+      "grad_norm": 0.9417083859443665,
+      "learning_rate": 0.0,
+      "loss": 0.6685,
+      "step": 30
+    },
+    {
+      "epoch": 0.0024968789013732834,
+      "eval_loss": 0.6942932605743408,
+      "eval_runtime": 483.6907,
+      "eval_samples_per_second": 10.459,
+      "eval_steps_per_second": 5.231,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -88,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5733274248806400.0,
+  "total_flos": 1.14665484976128e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null