Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69d2b6bc31e2993077bf3e7546117c2646664b08704744e2482fb415808eaf09
+oid sha256:d8435e9a43f79982ca2b08fe208d5dab6b34023066fc863215a728427542feb7
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f69a1978a28967b1a74ab50e2f0156ff4592fc71a5629d77bb266c03e219a231
+oid sha256:23326893a0a0937d471badc9a4003ca341db46054301ae12d16e291e7d425c15
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda721b5035b6c32d7353550a38d047ddb776a25e42cd15a85a63cb30e818647
+oid sha256:0a537322ad8b13e53e04e7307211efb0c953aabdad90bc42ba3149fe4980cca8
 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": 0.0007711884013264441,
+  "epoch": 0.0015423768026528882,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,221 @@
       "eval_samples_per_second": 9.654,
       "eval_steps_per_second": 1.207,
       "step": 25
+    },
+    {
+      "epoch": 0.0008020359373795018,
+      "grad_norm": 7.800178527832031,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 4.8528,
+      "step": 26
+    },
+    {
+      "epoch": 0.0008328834734325596,
+      "grad_norm": 7.349645137786865,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 4.1619,
+      "step": 27
+    },
+    {
+      "epoch": 0.0008637310094856173,
+      "grad_norm": 7.673518657684326,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 4.7956,
+      "step": 28
+    },
+    {
+      "epoch": 0.0008945785455386751,
+      "grad_norm": 10.641539573669434,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 4.3561,
+      "step": 29
+    },
+    {
+      "epoch": 0.0009254260815917329,
+      "grad_norm": 9.313581466674805,
+      "learning_rate": 5e-05,
+      "loss": 4.6394,
+      "step": 30
+    },
+    {
+      "epoch": 0.0009254260815917329,
+      "eval_loss": 2.2952756881713867,
+      "eval_runtime": 2827.877,
+      "eval_samples_per_second": 9.654,
+      "eval_steps_per_second": 1.207,
+      "step": 30
+    },
+    {
+      "epoch": 0.0009562736176447907,
+      "grad_norm": 9.103066444396973,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 4.3205,
+      "step": 31
+    },
+    {
+      "epoch": 0.0009871211536978484,
+      "grad_norm": 8.474302291870117,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 4.5479,
+      "step": 32
+    },
+    {
+      "epoch": 0.001017968689750906,
+      "grad_norm": 8.064745903015137,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 4.4902,
+      "step": 33
+    },
+    {
+      "epoch": 0.001048816225803964,
+      "grad_norm": 10.089030265808105,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 4.7719,
+      "step": 34
+    },
+    {
+      "epoch": 0.0010796637618570217,
+      "grad_norm": 8.952753067016602,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 4.4059,
+      "step": 35
+    },
+    {
+      "epoch": 0.0010796637618570217,
+      "eval_loss": 2.26672101020813,
+      "eval_runtime": 2827.9684,
+      "eval_samples_per_second": 9.653,
+      "eval_steps_per_second": 1.207,
+      "step": 35
+    },
+    {
+      "epoch": 0.0011105112979100794,
+      "grad_norm": 8.924944877624512,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 4.4099,
+      "step": 36
+    },
+    {
+      "epoch": 0.0011413588339631371,
+      "grad_norm": 7.8870849609375,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 3.8415,
+      "step": 37
+    },
+    {
+      "epoch": 0.001172206370016195,
+      "grad_norm": 7.664583683013916,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 4.1158,
+      "step": 38
+    },
+    {
+      "epoch": 0.0012030539060692528,
+      "grad_norm": 7.277047157287598,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 4.5537,
+      "step": 39
+    },
+    {
+      "epoch": 0.0012339014421223105,
+      "grad_norm": 9.538818359375,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 4.6796,
+      "step": 40
+    },
+    {
+      "epoch": 0.0012339014421223105,
+      "eval_loss": 2.2513623237609863,
+      "eval_runtime": 2828.1493,
+      "eval_samples_per_second": 9.653,
+      "eval_steps_per_second": 1.207,
+      "step": 40
+    },
+    {
+      "epoch": 0.0012647489781753682,
+      "grad_norm": 8.616003036499023,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 4.4239,
+      "step": 41
+    },
+    {
+      "epoch": 0.001295596514228426,
+      "grad_norm": 7.7439398765563965,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 4.3809,
+      "step": 42
+    },
+    {
+      "epoch": 0.0013264440502814838,
+      "grad_norm": 10.247624397277832,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 5.0836,
+      "step": 43
+    },
+    {
+      "epoch": 0.0013572915863345415,
+      "grad_norm": 7.0781731605529785,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 4.4539,
+      "step": 44
+    },
+    {
+      "epoch": 0.0013881391223875992,
+      "grad_norm": 7.964367866516113,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 4.6594,
+      "step": 45
+    },
+    {
+      "epoch": 0.0013881391223875992,
+      "eval_loss": 2.2453179359436035,
+      "eval_runtime": 2827.9873,
+      "eval_samples_per_second": 9.653,
+      "eval_steps_per_second": 1.207,
+      "step": 45
+    },
+    {
+      "epoch": 0.0014189866584406572,
+      "grad_norm": 9.104546546936035,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 4.7814,
+      "step": 46
+    },
+    {
+      "epoch": 0.0014498341944937149,
+      "grad_norm": 7.842891216278076,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 4.5211,
+      "step": 47
+    },
+    {
+      "epoch": 0.0014806817305467726,
+      "grad_norm": 7.90324068069458,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 4.689,
+      "step": 48
+    },
+    {
+      "epoch": 0.0015115292665998303,
+      "grad_norm": 7.208617687225342,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 4.5334,
+      "step": 49
+    },
+    {
+      "epoch": 0.0015423768026528882,
+      "grad_norm": 7.687088489532471,
+      "learning_rate": 0.0,
+      "loss": 4.5344,
+      "step": 50
+    },
+    {
+      "epoch": 0.0015423768026528882,
+      "eval_loss": 2.244182825088501,
+      "eval_runtime": 2829.169,
+      "eval_samples_per_second": 9.649,
+      "eval_steps_per_second": 1.206,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -244,12 +459,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.75782575996928e+16,
+  "total_flos": 3.51565151993856e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null