Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1714a655ccbc248f8d6f0215f4266deaf5a9eaccd73be7d2523b3d4b61e3a992
+oid sha256:6f9f18c1ad44f2f0153a218f1e3c421986b3ee8d5f6a3f8fb35f894277e304e7
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0f50378d5c8d3e98cebec88f5b760c42598a0cf0af7aeef58cb56363cbb65ea
+oid sha256:687da7444ba27aa10f5992fbaecb623c9df2c13b9aac211a99fb101eb7aebf2e
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a99204cca88fde91ee5434d3af31a06dcda5ff2ddb9b039866dfcf1cfee8f1fb
+oid sha256:f2d6fc726dea8bf2fd2bfce54e95b8b51620b69a9b06ce9d8f9a6981c9beb587
 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": 0.08818342151675485,
+  "epoch": 0.1763668430335097,
   "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": 9.21,
       "eval_steps_per_second": 1.156,
       "step": 25
+    },
+    {
+      "epoch": 0.09171075837742504,
+      "grad_norm": 0.30482396483421326,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.7513,
+      "step": 26
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 0.30801886320114136,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 1.8961,
+      "step": 27
+    },
+    {
+      "epoch": 0.09876543209876543,
+      "grad_norm": 0.26133787631988525,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 1.9043,
+      "step": 28
+    },
+    {
+      "epoch": 0.10229276895943562,
+      "grad_norm": 0.2819058895111084,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 1.7855,
+      "step": 29
+    },
+    {
+      "epoch": 0.10582010582010581,
+      "grad_norm": 0.312527596950531,
+      "learning_rate": 5e-05,
+      "loss": 1.9985,
+      "step": 30
+    },
+    {
+      "epoch": 0.10582010582010581,
+      "eval_loss": 1.9047672748565674,
+      "eval_runtime": 25.9486,
+      "eval_samples_per_second": 9.211,
+      "eval_steps_per_second": 1.156,
+      "step": 30
+    },
+    {
+      "epoch": 0.10934744268077601,
+      "grad_norm": 0.3022180497646332,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 1.892,
+      "step": 31
+    },
+    {
+      "epoch": 0.1128747795414462,
+      "grad_norm": 0.2602643370628357,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.015,
+      "step": 32
+    },
+    {
+      "epoch": 0.1164021164021164,
+      "grad_norm": 0.29187506437301636,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 1.7977,
+      "step": 33
+    },
+    {
+      "epoch": 0.11992945326278659,
+      "grad_norm": 0.32443922758102417,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.0107,
+      "step": 34
+    },
+    {
+      "epoch": 0.12345679012345678,
+      "grad_norm": 0.3862663507461548,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.9873,
+      "step": 35
+    },
+    {
+      "epoch": 0.12345679012345678,
+      "eval_loss": 1.9003955125808716,
+      "eval_runtime": 25.9507,
+      "eval_samples_per_second": 9.21,
+      "eval_steps_per_second": 1.156,
+      "step": 35
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 0.2514958381652832,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 1.8633,
+      "step": 36
+    },
+    {
+      "epoch": 0.13051146384479717,
+      "grad_norm": 0.3014344274997711,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 1.817,
+      "step": 37
+    },
+    {
+      "epoch": 0.13403880070546736,
+      "grad_norm": 0.28053081035614014,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.8325,
+      "step": 38
+    },
+    {
+      "epoch": 0.13756613756613756,
+      "grad_norm": 0.25218141078948975,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 1.8678,
+      "step": 39
+    },
+    {
+      "epoch": 0.14109347442680775,
+      "grad_norm": 0.3820461928844452,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.9818,
+      "step": 40
+    },
+    {
+      "epoch": 0.14109347442680775,
+      "eval_loss": 1.8975144624710083,
+      "eval_runtime": 25.9847,
+      "eval_samples_per_second": 9.198,
+      "eval_steps_per_second": 1.155,
+      "step": 40
+    },
+    {
+      "epoch": 0.14462081128747795,
+      "grad_norm": 0.29229605197906494,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 1.7644,
+      "step": 41
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.2876432538032532,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.0279,
+      "step": 42
+    },
+    {
+      "epoch": 0.15167548500881833,
+      "grad_norm": 0.3308974802494049,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 1.9899,
+      "step": 43
+    },
+    {
+      "epoch": 0.15520282186948853,
+      "grad_norm": 0.2830653488636017,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.8475,
+      "step": 44
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": 0.2673850655555725,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.8772,
+      "step": 45
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "eval_loss": 1.896990180015564,
+      "eval_runtime": 25.9369,
+      "eval_samples_per_second": 9.215,
+      "eval_steps_per_second": 1.157,
+      "step": 45
+    },
+    {
+      "epoch": 0.16225749559082892,
+      "grad_norm": 0.3193882405757904,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.0192,
+      "step": 46
+    },
+    {
+      "epoch": 0.1657848324514991,
+      "grad_norm": 0.278481662273407,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 1.7562,
+      "step": 47
+    },
+    {
+      "epoch": 0.1693121693121693,
+      "grad_norm": 0.3137940466403961,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 1.8002,
+      "step": 48
+    },
+    {
+      "epoch": 0.1728395061728395,
+      "grad_norm": 0.2706012725830078,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 1.99,
+      "step": 49
+    },
+    {
+      "epoch": 0.1763668430335097,
+      "grad_norm": 0.2629629671573639,
+      "learning_rate": 0.0,
+      "loss": 1.7014,
+      "step": 50
+    },
+    {
+      "epoch": 0.1763668430335097,
+      "eval_loss": 1.8965520858764648,
+      "eval_runtime": 25.9579,
+      "eval_samples_per_second": 9.207,
+      "eval_steps_per_second": 1.156,
+      "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": 1.852452537316147e+16,
+  "total_flos": 3.63500120529961e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null