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:f75b70b76f1aec56b74984bf133b73dffe581c2de3ce1ef11ce02272bd0a8838
+oid sha256:7ac437088b3707b1551e35da17c158e2399478f64273cc3d034ccc66c35c377a
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:963d868253b73bdf6c931559833bbd00790142e541e54fe267f9933de898efdd
+oid sha256:9d8aceadf4d0081513a3dd33114ccd5dd8c9f7a5d9def729d0aa5cf8eea133d4
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46c784a60f4659800f3c4472f150d377d77a69d88547c6e5e024a7e54b3ef12b
+oid sha256:a080d3277fb6ccb5ed989cb90ca2c5dbb10923ca8748d5a82c16ca3dd1e9dbd3
 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": 0.06851119894598155,
+  "epoch": 0.0878348704435661,
   "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": 44.3019,
       "step": 35
+    },
+    {
+      "epoch": 0.07026789635485288,
+      "grad_norm": 0.48046568036079407,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 44.2978,
+      "step": 40
+    },
+    {
+      "epoch": 0.07026789635485288,
+      "eval_loss": 11.074297904968262,
+      "eval_runtime": 1.4162,
+      "eval_samples_per_second": 169.463,
+      "eval_steps_per_second": 84.731,
+      "step": 40
+    },
+    {
+      "epoch": 0.07905138339920949,
+      "grad_norm": 0.47706079483032227,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 44.2985,
+      "step": 45
+    },
+    {
+      "epoch": 0.0878348704435661,
+      "grad_norm": 0.4358697533607483,
+      "learning_rate": 0.0,
+      "loss": 44.296,
+      "step": 50
+    },
+    {
+      "epoch": 0.0878348704435661,
+      "eval_loss": 11.074076652526855,
+      "eval_runtime": 1.383,
+      "eval_samples_per_second": 173.539,
+      "eval_steps_per_second": 86.769,
+      "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": 34927411200.0,
+  "total_flos": 43892736000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null