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:ec6efdfce441a24b991892096aed2904b0f74f74c6746dd922bec19494ba5f2c
+oid sha256:fcc30891b3e2477692c446e5a2e39c6c02ce7519960cd48dd0b284afc0107b06
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c0149703774f6a39651a93cb636cc3a92b4cb6f268c7e28e76f2fe6a6d242fc
+oid sha256:fca5d09a2e4ba8a69b0e79377846b39b458d784d3988d6057a61d0bc82e35f12
 size 1001863522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6a476a3e8189b0c4111bfdcfbeee5cdbfaae363703871898faa9453c66829c1
+oid sha256:6ede12a8e5b8050d6036f97afe9767dfe5a4d700916c846f5d58548015bfd6ae
 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": 0.02106149957877001,
+  "epoch": 0.04212299915754002,
   "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": 2.879,
       "eval_steps_per_second": 1.439,
       "step": 25
+    },
+    {
+      "epoch": 0.02190395956192081,
+      "grad_norm": 0.028270624577999115,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0004,
+      "step": 26
+    },
+    {
+      "epoch": 0.02274641954507161,
+      "grad_norm": 23.80878257751465,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.5098,
+      "step": 27
+    },
+    {
+      "epoch": 0.02358887952822241,
+      "grad_norm": 0.35975217819213867,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.0024,
+      "step": 28
+    },
+    {
+      "epoch": 0.02443133951137321,
+      "grad_norm": 0.03584504872560501,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 0.0004,
+      "step": 29
+    },
+    {
+      "epoch": 0.02527379949452401,
+      "grad_norm": 26.699068069458008,
+      "learning_rate": 5e-05,
+      "loss": 1.8089,
+      "step": 30
+    },
+    {
+      "epoch": 0.02527379949452401,
+      "eval_loss": 0.186017706990242,
+      "eval_runtime": 173.7954,
+      "eval_samples_per_second": 2.877,
+      "eval_steps_per_second": 1.438,
+      "step": 30
+    },
+    {
+      "epoch": 0.02611625947767481,
+      "grad_norm": 0.14413127303123474,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 0.0016,
+      "step": 31
+    },
+    {
+      "epoch": 0.02695871946082561,
+      "grad_norm": 29.635786056518555,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.6055,
+      "step": 32
+    },
+    {
+      "epoch": 0.02780117944397641,
+      "grad_norm": 0.8088165521621704,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.0077,
+      "step": 33
+    },
+    {
+      "epoch": 0.02864363942712721,
+      "grad_norm": 2.861088752746582,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0247,
+      "step": 34
+    },
+    {
+      "epoch": 0.02948609941027801,
+      "grad_norm": 18.717876434326172,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.3383,
+      "step": 35
+    },
+    {
+      "epoch": 0.02948609941027801,
+      "eval_loss": 0.16723041236400604,
+      "eval_runtime": 173.5378,
+      "eval_samples_per_second": 2.881,
+      "eval_steps_per_second": 1.441,
+      "step": 35
+    },
+    {
+      "epoch": 0.030328559393428812,
+      "grad_norm": 0.014492079615592957,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.0001,
+      "step": 36
+    },
+    {
+      "epoch": 0.031171019376579612,
+      "grad_norm": 0.3096715211868286,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.0009,
+      "step": 37
+    },
+    {
+      "epoch": 0.03201347935973041,
+      "grad_norm": 0.7171255946159363,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0056,
+      "step": 38
+    },
+    {
+      "epoch": 0.03285593934288121,
+      "grad_norm": 7.227740287780762,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 1.6772,
+      "step": 39
+    },
+    {
+      "epoch": 0.03369839932603201,
+      "grad_norm": 2.8483614921569824,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0192,
+      "step": 40
+    },
+    {
+      "epoch": 0.03369839932603201,
+      "eval_loss": 0.16995348036289215,
+      "eval_runtime": 173.7827,
+      "eval_samples_per_second": 2.877,
+      "eval_steps_per_second": 1.439,
+      "step": 40
+    },
+    {
+      "epoch": 0.03454085930918281,
+      "grad_norm": 27.91986846923828,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.6905,
+      "step": 41
+    },
+    {
+      "epoch": 0.03538331929233361,
+      "grad_norm": 2.2716541290283203,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0037,
+      "step": 42
+    },
+    {
+      "epoch": 0.03622577927548441,
+      "grad_norm": 17.69195556640625,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.9846,
+      "step": 43
+    },
+    {
+      "epoch": 0.03706823925863521,
+      "grad_norm": 0.016554847359657288,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0003,
+      "step": 44
+    },
+    {
+      "epoch": 0.037910699241786014,
+      "grad_norm": 22.69051742553711,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8968,
+      "step": 45
+    },
+    {
+      "epoch": 0.037910699241786014,
+      "eval_loss": 0.161066472530365,
+      "eval_runtime": 173.4454,
+      "eval_samples_per_second": 2.883,
+      "eval_steps_per_second": 1.441,
+      "step": 45
+    },
+    {
+      "epoch": 0.038753159224936815,
+      "grad_norm": 18.26679039001465,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.2506,
+      "step": 46
+    },
+    {
+      "epoch": 0.039595619208087615,
+      "grad_norm": 9.677942276000977,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 1.4274,
+      "step": 47
+    },
+    {
+      "epoch": 0.040438079191238416,
+      "grad_norm": 0.025408614426851273,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.0002,
+      "step": 48
+    },
+    {
+      "epoch": 0.041280539174389216,
+      "grad_norm": 7.174172878265381,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 1.445,
+      "step": 49
+    },
+    {
+      "epoch": 0.04212299915754002,
+      "grad_norm": 29.483102798461914,
+      "learning_rate": 0.0,
+      "loss": 0.337,
+      "step": 50
+    },
+    {
+      "epoch": 0.04212299915754002,
+      "eval_loss": 0.15462256968021393,
+      "eval_runtime": 173.4693,
+      "eval_samples_per_second": 2.882,
+      "eval_steps_per_second": 1.441,
+      "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": 3.1892762001408e+16,
+  "total_flos": 6.3785524002816e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null