Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b888d4284f3309f4953d9296462e335ef3cb10aa83c8ef130084d3be0cfe4fbc
+oid sha256:cb5b72bc8d0e458573c658687abb4633f44fd9fd20f88558dcf2acf599df294a
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:318776875314dbcf65169970b02b35c6f04e8a0cdc73c93c709b043ac3aa0f7c
+oid sha256:ccf9adc66cbb0077932da357fe37f224620076514c24fed94deb6d2e699fbdce
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b47570bd776ff9b913a0173d38ae3556b2b39014d19783889ceba3d9197ffba3
+oid sha256:d8314c1aff59c7b7de722e1163cb363999fcad04104d2d4997bd34eb4efa452a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
+oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0021092874563311582,
+  "epoch": 0.002636609320413948,
   "eval_steps": 2,
-  "global_step": 4,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,13 @@
       "eval_samples_per_second": 37.256,
       "eval_steps_per_second": 18.628,
       "step": 4
+    },
+    {
+      "epoch": 0.002636609320413948,
+      "grad_norm": 4.579606056213379,
+      "learning_rate": 5e-05,
+      "loss": 58.7084,
+      "step": 5
     }
   ],
   "logging_steps": 1,
@@ -73,12 +80,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2685013629861888.0,
+  "total_flos": 3350529828716544.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null