Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:107427ccf934f239fff348247e434764583c3dcf58ac97e1163693cc88454c6a
+oid sha256:ac460b921206649a8bd5c187cf68c886987893241d754a8bbd8c670a5ba531f3
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eabdac8aaceb3f5923afb2ceba185ff7d6b064038d48f09db3c52ce7687c0ad
+oid sha256:9e5ecbc0f116e2ea57057287c76654c954bbebc90fe157d373d9101ff20df19e
 size 194840426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24c6450e1837d5526408b4bd8d377053444beb9806a73b0e544c28e5aa498a07
+oid sha256:e8d4d0cc85b1e84b48e05e8bdab0ee06fe0f9dfd236b39151fefd8b6748b150c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:040b95482c646935022d148ebc91f462fbf2195cfa3365adbbe3bd6ca1f35a74
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1466275659824047,
+  "epoch": 0.2932551319648094,
   "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": 8.526,
       "eval_steps_per_second": 4.263,
       "step": 25
+    },
+    {
+      "epoch": 0.15249266862170088,
+      "grad_norm": 0.13398674130439758,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.2284,
+      "step": 26
+    },
+    {
+      "epoch": 0.15835777126099707,
+      "grad_norm": 0.13179174065589905,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 1.2156,
+      "step": 27
+    },
+    {
+      "epoch": 0.16422287390029325,
+      "grad_norm": 0.13458813726902008,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 1.2,
+      "step": 28
+    },
+    {
+      "epoch": 0.17008797653958943,
+      "grad_norm": 0.13363105058670044,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 1.2103,
+      "step": 29
+    },
+    {
+      "epoch": 0.17595307917888564,
+      "grad_norm": 0.1314612627029419,
+      "learning_rate": 0.0001,
+      "loss": 1.1684,
+      "step": 30
+    },
+    {
+      "epoch": 0.17595307917888564,
+      "eval_loss": 1.2251811027526855,
+      "eval_runtime": 16.8729,
+      "eval_samples_per_second": 8.534,
+      "eval_steps_per_second": 4.267,
+      "step": 30
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 0.12895148992538452,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 1.249,
+      "step": 31
+    },
+    {
+      "epoch": 0.187683284457478,
+      "grad_norm": 0.13325552642345428,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.2044,
+      "step": 32
+    },
+    {
+      "epoch": 0.1935483870967742,
+      "grad_norm": 0.13450513780117035,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 1.2241,
+      "step": 33
+    },
+    {
+      "epoch": 0.19941348973607037,
+      "grad_norm": 0.1256338208913803,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.1874,
+      "step": 34
+    },
+    {
+      "epoch": 0.20527859237536658,
+      "grad_norm": 0.1309565156698227,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.2098,
+      "step": 35
+    },
+    {
+      "epoch": 0.20527859237536658,
+      "eval_loss": 1.2191522121429443,
+      "eval_runtime": 16.8692,
+      "eval_samples_per_second": 8.536,
+      "eval_steps_per_second": 4.268,
+      "step": 35
+    },
+    {
+      "epoch": 0.21114369501466276,
+      "grad_norm": 0.1323598474264145,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 1.2083,
+      "step": 36
+    },
+    {
+      "epoch": 0.21700879765395895,
+      "grad_norm": 0.13297124207019806,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 1.2282,
+      "step": 37
+    },
+    {
+      "epoch": 0.22287390029325513,
+      "grad_norm": 0.1351737082004547,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.2235,
+      "step": 38
+    },
+    {
+      "epoch": 0.2287390029325513,
+      "grad_norm": 0.12594950199127197,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 1.2334,
+      "step": 39
+    },
+    {
+      "epoch": 0.23460410557184752,
+      "grad_norm": 0.12735791504383087,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 1.2064,
+      "step": 40
+    },
+    {
+      "epoch": 0.23460410557184752,
+      "eval_loss": 1.2153379917144775,
+      "eval_runtime": 16.8863,
+      "eval_samples_per_second": 8.528,
+      "eval_steps_per_second": 4.264,
+      "step": 40
+    },
+    {
+      "epoch": 0.2404692082111437,
+      "grad_norm": 0.13136377930641174,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 1.2058,
+      "step": 41
+    },
+    {
+      "epoch": 0.24633431085043989,
+      "grad_norm": 0.1283351331949234,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.2138,
+      "step": 42
+    },
+    {
+      "epoch": 0.25219941348973607,
+      "grad_norm": 0.13011294603347778,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 1.2674,
+      "step": 43
+    },
+    {
+      "epoch": 0.25806451612903225,
+      "grad_norm": 0.13453038036823273,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.1848,
+      "step": 44
+    },
+    {
+      "epoch": 0.26392961876832843,
+      "grad_norm": 0.13216698169708252,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 1.2187,
+      "step": 45
+    },
+    {
+      "epoch": 0.26392961876832843,
+      "eval_loss": 1.2136825323104858,
+      "eval_runtime": 16.8847,
+      "eval_samples_per_second": 8.528,
+      "eval_steps_per_second": 4.264,
+      "step": 45
+    },
+    {
+      "epoch": 0.2697947214076246,
+      "grad_norm": 0.12904256582260132,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 1.2266,
+      "step": 46
+    },
+    {
+      "epoch": 0.2756598240469208,
+      "grad_norm": 0.12724314630031586,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 1.238,
+      "step": 47
+    },
+    {
+      "epoch": 0.28152492668621704,
+      "grad_norm": 0.13328920304775238,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 1.1898,
+      "step": 48
+    },
+    {
+      "epoch": 0.2873900293255132,
+      "grad_norm": 0.12978258728981018,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 1.1839,
+      "step": 49
+    },
+    {
+      "epoch": 0.2932551319648094,
+      "grad_norm": 0.1395004689693451,
+      "learning_rate": 0.0,
+      "loss": 1.2598,
+      "step": 50
+    },
+    {
+      "epoch": 0.2932551319648094,
+      "eval_loss": 1.21341872215271,
+      "eval_runtime": 16.8832,
+      "eval_samples_per_second": 8.529,
+      "eval_steps_per_second": 4.265,
+      "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": 2.787855821910835e+16,
+  "total_flos": 5.582698751144755e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null