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:cd0d751caca88254b28936a58522309ff5e084e8855d0a2601aba67d3d2a2197
+oid sha256:e9d0110f662d8178e9b0b05d88d1d86b8145af66efe7a5c169bab444c9d6fbba
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16e216a48314993879ea42d3ea750ecfdc31febddc7969a859bace4e258946fe
+oid sha256:3c799607c0297cfc919efb1394aed8498094f20fda2c96a959f609553ad05596
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda721b5035b6c32d7353550a38d047ddb776a25e42cd15a85a63cb30e818647
+oid sha256:ed18caa550743cc0ff493b21980e76d2b6101c8cb9d8d39b72023be0a71b7d1b
 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": 0.5494505494505495,
+  "epoch": 1.098901098901099,
   "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": 9.066,
       "eval_steps_per_second": 1.193,
       "step": 25
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.810011625289917,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.6951,
+      "step": 26
+    },
+    {
+      "epoch": 0.5934065934065934,
+      "grad_norm": 0.877398669719696,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 1.8005,
+      "step": 27
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.7787519693374634,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 1.756,
+      "step": 28
+    },
+    {
+      "epoch": 0.6373626373626373,
+      "grad_norm": 0.7537305355072021,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 1.65,
+      "step": 29
+    },
+    {
+      "epoch": 0.6593406593406593,
+      "grad_norm": 0.7656542062759399,
+      "learning_rate": 5e-05,
+      "loss": 1.7674,
+      "step": 30
+    },
+    {
+      "epoch": 0.6593406593406593,
+      "eval_loss": 1.7136679887771606,
+      "eval_runtime": 4.1965,
+      "eval_samples_per_second": 9.055,
+      "eval_steps_per_second": 1.191,
+      "step": 30
+    },
+    {
+      "epoch": 0.6813186813186813,
+      "grad_norm": 0.8931242823600769,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 1.8151,
+      "step": 31
+    },
+    {
+      "epoch": 0.7032967032967034,
+      "grad_norm": 0.7679211497306824,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.6152,
+      "step": 32
+    },
+    {
+      "epoch": 0.7252747252747253,
+      "grad_norm": 0.873238205909729,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 1.7821,
+      "step": 33
+    },
+    {
+      "epoch": 0.7472527472527473,
+      "grad_norm": 0.9136878252029419,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.7956,
+      "step": 34
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.8463249802589417,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.6114,
+      "step": 35
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "eval_loss": 1.7016370296478271,
+      "eval_runtime": 4.1923,
+      "eval_samples_per_second": 9.064,
+      "eval_steps_per_second": 1.193,
+      "step": 35
+    },
+    {
+      "epoch": 0.7912087912087912,
+      "grad_norm": 0.8765092492103577,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 1.7043,
+      "step": 36
+    },
+    {
+      "epoch": 0.8131868131868132,
+      "grad_norm": 0.8109530806541443,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 1.6251,
+      "step": 37
+    },
+    {
+      "epoch": 0.8351648351648352,
+      "grad_norm": 0.8340989351272583,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.7425,
+      "step": 38
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.8605973720550537,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 1.6046,
+      "step": 39
+    },
+    {
+      "epoch": 0.8791208791208791,
+      "grad_norm": 0.755109429359436,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.596,
+      "step": 40
+    },
+    {
+      "epoch": 0.8791208791208791,
+      "eval_loss": 1.694095253944397,
+      "eval_runtime": 4.1958,
+      "eval_samples_per_second": 9.057,
+      "eval_steps_per_second": 1.192,
+      "step": 40
+    },
+    {
+      "epoch": 0.9010989010989011,
+      "grad_norm": 0.9387856721878052,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 1.7366,
+      "step": 41
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.7933199405670166,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.7872,
+      "step": 42
+    },
+    {
+      "epoch": 0.945054945054945,
+      "grad_norm": 0.9673396348953247,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 1.7465,
+      "step": 43
+    },
+    {
+      "epoch": 0.967032967032967,
+      "grad_norm": 0.8617414832115173,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.5447,
+      "step": 44
+    },
+    {
+      "epoch": 0.989010989010989,
+      "grad_norm": 0.8178028464317322,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7132,
+      "step": 45
+    },
+    {
+      "epoch": 0.989010989010989,
+      "eval_loss": 1.6919617652893066,
+      "eval_runtime": 4.1929,
+      "eval_samples_per_second": 9.063,
+      "eval_steps_per_second": 1.193,
+      "step": 45
+    },
+    {
+      "epoch": 1.010989010989011,
+      "grad_norm": 2.6103384494781494,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.3518,
+      "step": 46
+    },
+    {
+      "epoch": 1.032967032967033,
+      "grad_norm": 0.7555728554725647,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 1.6454,
+      "step": 47
+    },
+    {
+      "epoch": 1.054945054945055,
+      "grad_norm": 0.8182499408721924,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 1.525,
+      "step": 48
+    },
+    {
+      "epoch": 1.0769230769230769,
+      "grad_norm": 0.8152127861976624,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 1.8957,
+      "step": 49
+    },
+    {
+      "epoch": 1.098901098901099,
+      "grad_norm": 0.7147014737129211,
+      "learning_rate": 0.0,
+      "loss": 1.358,
+      "step": 50
+    },
+    {
+      "epoch": 1.098901098901099,
+      "eval_loss": 1.6911541223526,
+      "eval_runtime": 4.1933,
+      "eval_samples_per_second": 9.062,
+      "eval_steps_per_second": 1.192,
+      "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": 3.681615644668723e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null