Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -23,10 +23,10 @@
     "gate_proj",
     "up_proj",
     "down_proj",
+    "v_proj",
     "o_proj",
     "k_proj",
-    "q_proj",
-    "v_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c238ac1b6a4b9b698e95d33a2baec8d8bd8b494b0c3ef9d81a034fd68b4296ce
+oid sha256:4ba094ad598aa95aed793b98e633eadfb86c62b48584ff1c483f91e725531d2b
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:407387cec727e8e291a29aa4ecbf5b8318069046d389404a9f49a22ccd2a8c3b
+oid sha256:71f907b8c59d869733baaeafd9d203d6e40b2bebb4873d145e497d995a6982d8
 size 39398

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d72d7ea22c77570d9f0b88ee6c374873539a76f4bdfadda50933cc65992b9c8
+oid sha256:2ccb4f4fa4dcfe5bc230fa2b68534e99c4447a88f31286dfb471650fb9f2ed51
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8acd44aea89adc155a830cbfb990e7f2a2f3c98d29366996401b6b1b0b798b77
+oid sha256:c79f78716b356923e3a954e645268f3247781e92319c3c3c699c29edf2344335
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011217049915872126,
+  "epoch": 0.0033651149747616375,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.0011217049915872126,
-      "grad_norm": 0.010464487597346306,
+      "grad_norm": 0.010207759216427803,
       "learning_rate": 2e-05,
       "loss": 11.9305,
       "step": 1
@@ -18,21 +18,21 @@
     {
       "epoch": 0.0011217049915872126,
       "eval_loss": 11.931302070617676,
-      "eval_runtime": 1.6109,
-      "eval_samples_per_second": 466.206,
-      "eval_steps_per_second": 116.707,
+      "eval_runtime": 1.5864,
+      "eval_samples_per_second": 473.392,
+      "eval_steps_per_second": 118.506,
       "step": 1
     },
     {
       "epoch": 0.002243409983174425,
-      "grad_norm": 0.012750067748129368,
+      "grad_norm": 0.014218014664947987,
       "learning_rate": 4e-05,
       "loss": 11.9324,
       "step": 2
     },
     {
       "epoch": 0.0033651149747616375,
-      "grad_norm": 0.01111360639333725,
+      "grad_norm": 0.01008047629147768,
       "learning_rate": 6e-05,
       "loss": 11.9253,
       "step": 3
@@ -40,75 +40,10 @@
     {
       "epoch": 0.0033651149747616375,
       "eval_loss": 11.931297302246094,
-      "eval_runtime": 1.6294,
-      "eval_samples_per_second": 460.916,
-      "eval_steps_per_second": 115.382,
+      "eval_runtime": 1.6298,
+      "eval_samples_per_second": 460.789,
+      "eval_steps_per_second": 115.351,
       "step": 3
-    },
-    {
-      "epoch": 0.00448681996634885,
-      "grad_norm": 0.0054331207647919655,
-      "learning_rate": 8e-05,
-      "loss": 11.9339,
-      "step": 4
-    },
-    {
-      "epoch": 0.005608524957936063,
-      "grad_norm": 0.008967204950749874,
-      "learning_rate": 0.0001,
-      "loss": 11.9314,
-      "step": 5
-    },
-    {
-      "epoch": 0.006730229949523275,
-      "grad_norm": 0.01504911296069622,
-      "learning_rate": 0.00012,
-      "loss": 11.9317,
-      "step": 6
-    },
-    {
-      "epoch": 0.006730229949523275,
-      "eval_loss": 11.931279182434082,
-      "eval_runtime": 1.6578,
-      "eval_samples_per_second": 453.009,
-      "eval_steps_per_second": 113.403,
-      "step": 6
-    },
-    {
-      "epoch": 0.007851934941110488,
-      "grad_norm": 0.015188493765890598,
-      "learning_rate": 0.00014,
-      "loss": 11.927,
-      "step": 7
-    },
-    {
-      "epoch": 0.0089736399326977,
-      "grad_norm": 0.015619461424648762,
-      "learning_rate": 0.00016,
-      "loss": 11.9367,
-      "step": 8
-    },
-    {
-      "epoch": 0.010095344924284913,
-      "grad_norm": 0.010902787558734417,
-      "learning_rate": 0.00018,
-      "loss": 11.9306,
-      "step": 9
-    },
-    {
-      "epoch": 0.010095344924284913,
-      "eval_loss": 11.93125057220459,
-      "eval_runtime": 1.641,
-      "eval_samples_per_second": 457.636,
-      "eval_steps_per_second": 114.561,
-      "step": 9
-    },
-    {
-      "epoch": 0.011217049915872126,
-      "grad_norm": 0.010949921794235706,
-      "learning_rate": 0.0002,
-      "loss": 11.9328,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -123,12 +58,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 2392768512.0,
+  "total_flos": 738508800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2daceafefb5eef61850777c2a560f7c86e0e58a4e9e3449351c10cc0e181f086
+oid sha256:d2ce149ccbf74c75eb8c00802c87066be4e8f73892cf619b77e696423334565d
 size 6776