Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eb3100dd34ea951c363b8c05184404dcdb5dea9626726cfb806bc86780e7359
+oid sha256:9f9c6cb812db04a25eee144153688fcff1f97ea15bdeecf54a81d90e0914149b
 size 130583912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:290efce1f018ea8f532ea08a4d203f1e19a5977013b5af7e4d14b8872390c989
+oid sha256:b6425f231cd2e5f4faec2a2b985ed6b1a3d4b9a4704398f0e6899e72ddb808cf
 size 66578772

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec12f28e479716caa37a47da40d608c7ddf29f4c0d224be7900e717ee835399
+oid sha256:c7993a5258d45dec24981f6d3b745cb74af107efdbe9b02422eae54ccc57c63e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007611508601004719,
+  "epoch": 0.0015223017202009438,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 3.096,
       "eval_steps_per_second": 3.096,
       "step": 25
+    },
+    {
+      "epoch": 0.0009133810321205663,
+      "grad_norm": 5.164300441741943,
+      "learning_rate": 5e-05,
+      "loss": 2.1182,
+      "step": 30
+    },
+    {
+      "epoch": 0.0010656112041406607,
+      "grad_norm": 6.3647918701171875,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.9057,
+      "step": 35
+    },
+    {
+      "epoch": 0.001217841376160755,
+      "grad_norm": 10.471409797668457,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.7673,
+      "step": 40
+    },
+    {
+      "epoch": 0.0013700715481808495,
+      "grad_norm": 6.385285377502441,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7231,
+      "step": 45
+    },
+    {
+      "epoch": 0.0015223017202009438,
+      "grad_norm": 5.6406755447387695,
+      "learning_rate": 0.0,
+      "loss": 1.4536,
+      "step": 50
+    },
+    {
+      "epoch": 0.0015223017202009438,
+      "eval_loss": 1.7333505153656006,
+      "eval_runtime": 1178.0644,
+      "eval_samples_per_second": 3.098,
+      "eval_steps_per_second": 3.098,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -72,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2045610570547200.0,
+  "total_flos": 4091221141094400.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null