Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e266490a910b72109fb5a225424a673603a0530159ad44b7510f307cfd3c6d7
+oid sha256:3717784010f2586a268ec6c05be65873b3cb0983581f902a8cec5ceb504214b8
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36571baa81e0cc98a2e9355720fe26a928e5d253f84ae5739588b44f4a4dba4b
+oid sha256:39ec1904534117601d6c26bca80b2b66815cce15f44dbf46e04fcd0ba816fc42
 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": 0.0028115159694107063,
+  "epoch": 0.005623031938821413,
   "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": 9.055,
       "eval_steps_per_second": 1.132,
       "step": 25
+    },
+    {
+      "epoch": 0.0029239766081871343,
+      "grad_norm": 0.5085208415985107,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.9733,
+      "step": 26
+    },
+    {
+      "epoch": 0.003036437246963563,
+      "grad_norm": 0.5659909248352051,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 1.0632,
+      "step": 27
+    },
+    {
+      "epoch": 0.003148897885739991,
+      "grad_norm": 0.5472968816757202,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 1.0175,
+      "step": 28
+    },
+    {
+      "epoch": 0.0032613585245164192,
+      "grad_norm": 0.524185299873352,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 1.0288,
+      "step": 29
+    },
+    {
+      "epoch": 0.0033738191632928477,
+      "grad_norm": 0.5419555306434631,
+      "learning_rate": 5e-05,
+      "loss": 1.0801,
+      "step": 30
+    },
+    {
+      "epoch": 0.0033738191632928477,
+      "eval_loss": 1.0140562057495117,
+      "eval_runtime": 826.2541,
+      "eval_samples_per_second": 9.063,
+      "eval_steps_per_second": 1.133,
+      "step": 30
+    },
+    {
+      "epoch": 0.0034862798020692757,
+      "grad_norm": 0.44709768891334534,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 0.8995,
+      "step": 31
+    },
+    {
+      "epoch": 0.003598740440845704,
+      "grad_norm": 0.45280900597572327,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.0176,
+      "step": 32
+    },
+    {
+      "epoch": 0.003711201079622132,
+      "grad_norm": 0.4053972661495209,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.9466,
+      "step": 33
+    },
+    {
+      "epoch": 0.0038236617183985606,
+      "grad_norm": 0.4766600430011749,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.0009,
+      "step": 34
+    },
+    {
+      "epoch": 0.003936122357174989,
+      "grad_norm": 0.45294103026390076,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.0124,
+      "step": 35
+    },
+    {
+      "epoch": 0.003936122357174989,
+      "eval_loss": 1.0017218589782715,
+      "eval_runtime": 827.7032,
+      "eval_samples_per_second": 9.047,
+      "eval_steps_per_second": 1.131,
+      "step": 35
+    },
+    {
+      "epoch": 0.004048582995951417,
+      "grad_norm": 0.47154468297958374,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.9283,
+      "step": 36
+    },
+    {
+      "epoch": 0.0041610436347278455,
+      "grad_norm": 0.46065637469291687,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.9644,
+      "step": 37
+    },
+    {
+      "epoch": 0.004273504273504274,
+      "grad_norm": 0.43747445940971375,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.9395,
+      "step": 38
+    },
+    {
+      "epoch": 0.0043859649122807015,
+      "grad_norm": 0.4837368428707123,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.9991,
+      "step": 39
+    },
+    {
+      "epoch": 0.00449842555105713,
+      "grad_norm": 0.43076515197753906,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.9176,
+      "step": 40
+    },
+    {
+      "epoch": 0.00449842555105713,
+      "eval_loss": 0.9943129420280457,
+      "eval_runtime": 826.2381,
+      "eval_samples_per_second": 9.063,
+      "eval_steps_per_second": 1.133,
+      "step": 40
+    },
+    {
+      "epoch": 0.004610886189833558,
+      "grad_norm": 0.5260198712348938,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 1.0163,
+      "step": 41
+    },
+    {
+      "epoch": 0.004723346828609987,
+      "grad_norm": 0.4770829677581787,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.0087,
+      "step": 42
+    },
+    {
+      "epoch": 0.004835807467386414,
+      "grad_norm": 0.5031581521034241,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 1.0117,
+      "step": 43
+    },
+    {
+      "epoch": 0.004948268106162843,
+      "grad_norm": 0.5243813395500183,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.1394,
+      "step": 44
+    },
+    {
+      "epoch": 0.005060728744939271,
+      "grad_norm": 0.49357548356056213,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.002,
+      "step": 45
+    },
+    {
+      "epoch": 0.005060728744939271,
+      "eval_loss": 0.9909366965293884,
+      "eval_runtime": 825.9423,
+      "eval_samples_per_second": 9.066,
+      "eval_steps_per_second": 1.133,
+      "step": 45
+    },
+    {
+      "epoch": 0.0051731893837157,
+      "grad_norm": 0.46298205852508545,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.9586,
+      "step": 46
+    },
+    {
+      "epoch": 0.005285650022492127,
+      "grad_norm": 0.4490233063697815,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.9514,
+      "step": 47
+    },
+    {
+      "epoch": 0.005398110661268556,
+      "grad_norm": 0.44175946712493896,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.8795,
+      "step": 48
+    },
+    {
+      "epoch": 0.005510571300044984,
+      "grad_norm": 0.4616028368473053,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.9672,
+      "step": 49
+    },
+    {
+      "epoch": 0.005623031938821413,
+      "grad_norm": 0.456407368183136,
+      "learning_rate": 0.0,
+      "loss": 0.9266,
+      "step": 50
+    },
+    {
+      "epoch": 0.005623031938821413,
+      "eval_loss": 0.9902380108833313,
+      "eval_runtime": 826.0197,
+      "eval_samples_per_second": 9.065,
+      "eval_steps_per_second": 1.133,
+      "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": 1.85471820890112e+16,
+  "total_flos": 3.70943641780224e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null