Training in progress, step 10, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "down_proj",
+    "up_proj",
     "gate_proj",
     "k_proj",
-    "v_proj",
-    "o_proj",
     "q_proj",
-    "up_proj"
+    "v_proj",
+    "o_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 sha256:308a2ccf6c96552af4d193694fb61373688ca0bcf1ea1521c8a6b0e7ab3fe085
+oid sha256:21101be3f2578dea61017dec401770c9d94090e8c532e49059856959e61f6b55
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eab50c68ad1ce2e21fc33fccd16f7a19c69259dcb885320db7f6e8f2df485f1
+oid sha256:11e2baddaf1d69caca788f2f3a96826392458aa83f7fe994f7bd4067df65817f
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc6c1736fef1dd6f59b0e0436ac03f5bf52fc685c6304e2891f3922fbeca4f35
+oid sha256:5bcc9dec470456049b85d58761d8b1cb7c00e042c845ac37d7d42f59480fe0bd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,107 +1,114 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04845222072678331,
+  "epoch": 0.026917900403768506,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.005383580080753701,
-      "grad_norm": 1.332345962524414,
+      "epoch": 0.0026917900403768506,
+      "grad_norm": 1.408136248588562,
       "learning_rate": 2e-05,
-      "loss": 0.7345,
+      "loss": 0.7399,
       "step": 1
     },
     {
-      "epoch": 0.005383580080753701,
-      "eval_loss": 0.7382340431213379,
-      "eval_runtime": 7.7076,
-      "eval_samples_per_second": 10.25,
-      "eval_steps_per_second": 5.19,
+      "epoch": 0.0026917900403768506,
+      "eval_loss": 0.7382442355155945,
+      "eval_runtime": 6.3386,
+      "eval_samples_per_second": 12.463,
+      "eval_steps_per_second": 12.463,
       "step": 1
     },
     {
-      "epoch": 0.010767160161507403,
-      "grad_norm": 1.5144602060317993,
+      "epoch": 0.005383580080753701,
+      "grad_norm": 1.402262568473816,
       "learning_rate": 4e-05,
-      "loss": 0.7732,
+      "loss": 0.7274,
       "step": 2
     },
     {
-      "epoch": 0.016150740242261104,
-      "grad_norm": 1.4010770320892334,
+      "epoch": 0.008075370121130552,
+      "grad_norm": 1.6652259826660156,
       "learning_rate": 6e-05,
-      "loss": 0.7996,
+      "loss": 0.7714,
       "step": 3
     },
     {
-      "epoch": 0.016150740242261104,
-      "eval_loss": 0.6860002279281616,
-      "eval_runtime": 7.8686,
-      "eval_samples_per_second": 10.04,
-      "eval_steps_per_second": 5.083,
+      "epoch": 0.008075370121130552,
+      "eval_loss": 0.6933578848838806,
+      "eval_runtime": 6.3351,
+      "eval_samples_per_second": 12.47,
+      "eval_steps_per_second": 12.47,
       "step": 3
     },
     {
-      "epoch": 0.021534320323014805,
-      "grad_norm": 1.2587902545928955,
+      "epoch": 0.010767160161507403,
+      "grad_norm": 1.429751992225647,
       "learning_rate": 8e-05,
-      "loss": 0.665,
+      "loss": 0.7393,
       "step": 4
     },
     {
-      "epoch": 0.026917900403768506,
-      "grad_norm": 1.1400635242462158,
+      "epoch": 0.013458950201884253,
+      "grad_norm": 1.4376033544540405,
       "learning_rate": 0.0001,
-      "loss": 0.6649,
+      "loss": 0.7399,
       "step": 5
     },
     {
-      "epoch": 0.03230148048452221,
-      "grad_norm": 0.9094105362892151,
+      "epoch": 0.016150740242261104,
+      "grad_norm": 1.3412057161331177,
       "learning_rate": 0.00012,
-      "loss": 0.5525,
+      "loss": 0.6919,
       "step": 6
     },
     {
-      "epoch": 0.03230148048452221,
-      "eval_loss": 0.5270073413848877,
-      "eval_runtime": 7.7898,
-      "eval_samples_per_second": 10.141,
-      "eval_steps_per_second": 5.135,
+      "epoch": 0.016150740242261104,
+      "eval_loss": 0.5569691061973572,
+      "eval_runtime": 6.5483,
+      "eval_samples_per_second": 12.064,
+      "eval_steps_per_second": 12.064,
       "step": 6
     },
     {
-      "epoch": 0.03768506056527591,
-      "grad_norm": NaN,
-      "learning_rate": 0.00012,
-      "loss": 0.5412,
+      "epoch": 0.018842530282637954,
+      "grad_norm": 1.139148473739624,
+      "learning_rate": 0.00014,
+      "loss": 0.4971,
       "step": 7
     },
     {
-      "epoch": 0.04306864064602961,
-      "grad_norm": 0.9600444436073303,
-      "learning_rate": 0.00014,
-      "loss": 0.6705,
+      "epoch": 0.021534320323014805,
+      "grad_norm": 1.1586865186691284,
+      "learning_rate": 0.00016,
+      "loss": 0.4434,
       "step": 8
     },
     {
-      "epoch": 0.04845222072678331,
-      "grad_norm": 1.114023208618164,
-      "learning_rate": 0.00016,
-      "loss": 0.4857,
+      "epoch": 0.024226110363391656,
+      "grad_norm": 1.3152556419372559,
+      "learning_rate": 0.00018,
+      "loss": 0.4553,
       "step": 9
     },
     {
-      "epoch": 0.04845222072678331,
-      "eval_loss": 0.424485981464386,
-      "eval_runtime": 7.7991,
-      "eval_samples_per_second": 10.129,
-      "eval_steps_per_second": 5.129,
+      "epoch": 0.024226110363391656,
+      "eval_loss": 0.4071764349937439,
+      "eval_runtime": 6.4684,
+      "eval_samples_per_second": 12.213,
+      "eval_steps_per_second": 12.213,
       "step": 9
+    },
+    {
+      "epoch": 0.026917900403768506,
+      "grad_norm": 1.2165873050689697,
+      "learning_rate": 0.0002,
+      "loss": 0.4257,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4253997837844480.0,
+  "total_flos": 2358194416386048.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a212cd389246f94d793758aff17e074e70be0b5a2ee39d33914356f9a22c4aa
+oid sha256:add0e59b79de04b92c19a082f4b4bd8afdd3721024dd528eee811fafb0ec960e
 size 6776