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:fc4890f041c5bf42ffe4472e58bdba36b4a7f87cd2fbde92e944863bab9057ea
+oid sha256:2fa18d2c22893ab41e19e0490e76413381fb41075cc0bd2a19a8238d380eb82f
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fddd72353a93333665699717190c3b2d774d7bad2a224db9f7c8e219d29c467
+oid sha256:b5be8733985e07e3ffca1c61950df69bf7e85ff4ae536032e945ea6de5fefc60
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4237cffb2e3da44c4b7249d4b62710b8f45c2373714e723e7cfbe3fe6883a3d7
+oid sha256:b41d80c15f23cc68c5918c2d98bc69f2ddbb28c485bf495dc4a5ee3f38086157
 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": 0.010105092966855295,
+  "epoch": 0.02021018593371059,
   "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": 4.598,
       "eval_steps_per_second": 0.576,
       "step": 25
+    },
+    {
+      "epoch": 0.010509296685529508,
+      "grad_norm": 0.93433678150177,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.4645,
+      "step": 26
+    },
+    {
+      "epoch": 0.010913500404203719,
+      "grad_norm": 0.8287851810455322,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 2.6179,
+      "step": 27
+    },
+    {
+      "epoch": 0.01131770412287793,
+      "grad_norm": 0.8977319598197937,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 2.7171,
+      "step": 28
+    },
+    {
+      "epoch": 0.011721907841552142,
+      "grad_norm": 0.7713293433189392,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 2.6567,
+      "step": 29
+    },
+    {
+      "epoch": 0.012126111560226353,
+      "grad_norm": 0.7393156886100769,
+      "learning_rate": 5e-05,
+      "loss": 2.5136,
+      "step": 30
+    },
+    {
+      "epoch": 0.012126111560226353,
+      "eval_loss": 1.2371978759765625,
+      "eval_runtime": 453.0604,
+      "eval_samples_per_second": 4.6,
+      "eval_steps_per_second": 0.576,
+      "step": 30
+    },
+    {
+      "epoch": 0.012530315278900566,
+      "grad_norm": 0.6830640435218811,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 2.6676,
+      "step": 31
+    },
+    {
+      "epoch": 0.012934518997574777,
+      "grad_norm": 0.7319803237915039,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.3856,
+      "step": 32
+    },
+    {
+      "epoch": 0.01333872271624899,
+      "grad_norm": 0.7554514408111572,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 2.5566,
+      "step": 33
+    },
+    {
+      "epoch": 0.0137429264349232,
+      "grad_norm": 0.6606221795082092,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.3467,
+      "step": 34
+    },
+    {
+      "epoch": 0.014147130153597413,
+      "grad_norm": 0.6036873459815979,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.0719,
+      "step": 35
+    },
+    {
+      "epoch": 0.014147130153597413,
+      "eval_loss": 1.224223017692566,
+      "eval_runtime": 453.2044,
+      "eval_samples_per_second": 4.598,
+      "eval_steps_per_second": 0.576,
+      "step": 35
+    },
+    {
+      "epoch": 0.014551333872271624,
+      "grad_norm": 0.9149614572525024,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 2.2007,
+      "step": 36
+    },
+    {
+      "epoch": 0.014955537590945837,
+      "grad_norm": 0.47336137294769287,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 2.4277,
+      "step": 37
+    },
+    {
+      "epoch": 0.015359741309620048,
+      "grad_norm": 0.6594354510307312,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.8188,
+      "step": 38
+    },
+    {
+      "epoch": 0.01576394502829426,
+      "grad_norm": 0.6771719455718994,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 2.3827,
+      "step": 39
+    },
+    {
+      "epoch": 0.016168148746968473,
+      "grad_norm": 0.7665150761604309,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.6651,
+      "step": 40
+    },
+    {
+      "epoch": 0.016168148746968473,
+      "eval_loss": 1.2175811529159546,
+      "eval_runtime": 453.0444,
+      "eval_samples_per_second": 4.6,
+      "eval_steps_per_second": 0.576,
+      "step": 40
+    },
+    {
+      "epoch": 0.016572352465642683,
+      "grad_norm": 1.0414700508117676,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 2.9944,
+      "step": 41
+    },
+    {
+      "epoch": 0.016976556184316895,
+      "grad_norm": 0.7823891043663025,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.3473,
+      "step": 42
+    },
+    {
+      "epoch": 0.017380759902991108,
+      "grad_norm": 0.49085983633995056,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 2.2603,
+      "step": 43
+    },
+    {
+      "epoch": 0.01778496362166532,
+      "grad_norm": 0.7287192344665527,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 2.5286,
+      "step": 44
+    },
+    {
+      "epoch": 0.01818916734033953,
+      "grad_norm": 0.5006673336029053,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.0819,
+      "step": 45
+    },
+    {
+      "epoch": 0.01818916734033953,
+      "eval_loss": 1.215002417564392,
+      "eval_runtime": 453.0566,
+      "eval_samples_per_second": 4.6,
+      "eval_steps_per_second": 0.576,
+      "step": 45
+    },
+    {
+      "epoch": 0.018593371059013743,
+      "grad_norm": 0.6527900099754333,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.2517,
+      "step": 46
+    },
+    {
+      "epoch": 0.018997574777687955,
+      "grad_norm": 1.0630096197128296,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 2.9461,
+      "step": 47
+    },
+    {
+      "epoch": 0.019401778496362168,
+      "grad_norm": 0.761471152305603,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 2.2641,
+      "step": 48
+    },
+    {
+      "epoch": 0.019805982215036377,
+      "grad_norm": 0.7035945653915405,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 2.2215,
+      "step": 49
+    },
+    {
+      "epoch": 0.02021018593371059,
+      "grad_norm": 0.7908831238746643,
+      "learning_rate": 0.0,
+      "loss": 2.6591,
+      "step": 50
+    },
+    {
+      "epoch": 0.02021018593371059,
+      "eval_loss": 1.2144694328308105,
+      "eval_runtime": 453.5575,
+      "eval_samples_per_second": 4.595,
+      "eval_steps_per_second": 0.575,
+      "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": 3.300871580418048e+16,
+  "total_flos": 6.538264861212672e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null